Back to jobs

Senior LLM Training Engineer (Post-training)

WeWork Hanzomon (Hanzomon PREX North, 2-3-2 Kojimachi, Chiyoda-ku, Tokyo) Hybrid: mostly in the office, with some remote work. For candidates based outside Japan, remote arrangements are open to discussion.

Actively hiring, first seen by us 3 days ago
Pay
Multiple pay statements — pay source
You'll make Recho's AI models smarter for our use cases through post-training. You'll design the training methods, the reward design that "grades" the model, and the training data yourself, and you'll own the model's intelligence itself. Your job is to optimize general-purpose LLMs for our use cases, and down the line, we plan to offer that performance externally as an API business. **Team language:** English (Japanese not required) - **Salary:** ¥10M–¥20M per year, plus stock options - **Location:** Tokyo (Hanzomon), hybrid. Candidates based outside Japan are welcome. We offer visa sponsorship and relocation support, and we're open to discussing fully remote arrangements. ## You might be a fit if you are…
Compensation is based on your current compensation, skills and experience. **Annual salary:** ¥10M–¥20M - **Salary review:** Once a year, based on your contribution and company performance - **Stock option plan** 勤務地
Read the full posting
Work setting
Hybrid — work setting source
Listed location: WeWork Hanzomon (Hanzomon PREX North, 2-3-2 Kojimachi, Chiyoda-ku, Tokyo) Hybrid: mostly in the office, with some remote work. For candidates based outside Japan, remote arrangements are open to discussion.
Read the full posting
Employment
Full-time · Permanent — employment source
雇用形態 Employment type: Full-time, permanent. Starting with a paid contract engagement first is also an option. 勤務体系
Read the full posting

What you’ll work on

Full posting
  • Design, implement and run SFT, preference optimization and online RL such as GRPO

  • Build reward models, RLVR pipelines and LLM-as-a-Judge evaluation

  • Manage training data quality, mixture ratios and deduplication

  • Improve post-training algorithms such as loss functions and training stability

  • Design internal evaluation sets and build the evaluation platform

From the employer’s posting
Design, implement and run SFT, preference optimization (DPO, KTO, ORPO, SimPO, etc.) and online RL (PPO, GRPO, RLOO, etc.)
Build reward models, RLVR (verifiable rewards) and LLM-as-a-Judge pipelines
Generate synthetic data and manage data quality: mixture optimization, difficulty control, deduplication and benchmark contamination checks
Improve post-training algorithms: loss functions, KL penalty, advantage estimation, training stability and sample efficiency
Design new internal evaluation sets that correlate with product quality

Before you apply

Work authorization
Sponsors visas

What you’ll bring

All qualifications

Core experience

  • Deep work on LLM training, especially post-training
  • Has applied SFT, preference optimization or RLHF to a production model and shipped it
  • CS or math background (MS/PhD or equivalent industry experience)
  • Track record of conference publications or open-source work
Qualification wording
An ML engineer or researcher who has worked deeply on LLM training, especially post-training
Someone who has applied SFT, preference optimization or RLHF to a production model and shipped it
Someone with a CS or math background (MS/PhD, or equivalent industry experience)
a track record of conference publications or open-source work
Education & alternatives
## You might be a fit if you are… - An ML engineer or researcher who has worked deeply on LLM training, especially post-training - Someone who has applied SFT, preference optimization or RLHF to a production model and shipped it - Someone with a CS or math background (MS/PhD, or equivalent industry experience) and a track record of conference publications or open-source work ## About the role

Tools in this posting

  • Python
  • Kubernetes
  • PyTorch
Source — Tool mentions in context
## Tech stack - **Languages & frameworks:** Python, PyTorch - **Training methods:** SFT, DPO, KTO, ORPO, SimPO, PPO, GRPO, RLOO - **Rewards & evaluation:** Reward models, RLVR (verifiable rewards), LLM-as-a-Judge - **RL & distributed training:** verl, OpenRLHF, TRL, FSDP, DeepSpeed, Megatron-LM - **Rollout inference:** vLLM, SGLang - **Experiment tracking & compute:** Weights & Biases, etc.; Slurm, Kubernetes ## Our product
Apply at 株式会社Recho

Posting record

Report an error

Actively hiringFirst seen by us 3 days ago, still listed, and not a repost of an earlier posting.

Status in our records
Live
First seen by us
Nov 18, 20263 days ago
Recorded sightings
4
Last seen by us
Nov 21, 2026
Employer says posted
Oct 22, 2026

These dates show when we found the posting. Check the employer’s website to confirm it is still accepting applications.

How this job compares

Time since we first saw it

Day 3

Early. Similar jobs usually come down between day 7 and day 76.

From 6,389 similar postings that came down. Coming down is not always a hire.

株式会社Recho is hiring

5 open jobs

Open jobs by the week we first saw them, last 12 weeks.

Hiring record

Your next step

Complete your application on herp.careers. The employer’s form will show what is required.

Already applied? Track this application

Job description

View original posting ↗

Senior LLM Training Engineer (Post-training)

仕事概要

## In short

You'll make Recho's AI models smarter for our use cases through post-training. You'll design the training methods, the reward design that "grades" the model, and the training data yourself, and you'll own the model's intelligence itself. Your job is to optimize general-purpose LLMs for our use cases, and down the line, we plan to offer that performance externally as an API business.

- **Team language:** English (Japanese not required)
- **Salary:** ¥10M–¥20M per year, plus stock options
- **Location:** Tokyo (Hanzomon), hybrid. Candidates based outside Japan are welcome. We offer visa sponsorship and relocation support, and we're open to discussing fully remote arrangements.

## You might be a fit if you are…

- An ML engineer or researcher who has worked deeply on LLM training, especially post-training
- Someone who has applied SFT, preference optimization or RLHF to a production model and shipped it
- Someone with a CS or math background (MS/PhD, or equivalent industry experience) and a track record of conference publications or open-source work

## About the role

At Recho, we don't use general-purpose LLMs as they are. We optimize them for our use cases through post-training and build them deep into our product. Your core mission is to design, implement and run training methods such as SFT, preference optimization and reinforcement learning (RL), and to own training quality for post-training of a single model.

You'll work at the core of what makes the model smart. That includes reward design (reward models, RLVR, LLM-as-a-Judge), designing training data quality and mixture ratios, and improving the post-training algorithms themselves (loss functions, KL penalty, advantage estimation, training stability).

We also plan to offer the performance we gain here externally as an API and grow it into a second pillar of our business. The scope includes post-training for agentic use cases such as long CoT and reasoning, tool use and function calling.

## What this role is *not*

- Not an on-call or SRE role. SLA management, incident recovery and infrastructure maintenance for online services are not the focus.
- GPU cluster operations and general SRE/DevOps are handled by a separate team.
- Building the infrastructure that runs training and inference (rollout systems, weight sync, GPU allocation) belongs to our RL Infrastructure Engineer role. You'll own the algorithms, rewards and data, and partner with that team.
- Pre-training from scratch is not the main job. The focus is post-training.

## What you'll do

### 1. Design, implement and run post-training

- Design, implement and run SFT, preference optimization (DPO, KTO, ORPO, SimPO, etc.) and online RL (PPO, GRPO, RLOO, etc.)
- Post-training for long CoT and reasoning, tool use, function calling and agentic use cases
- Improve post-training algorithms: loss functions, KL penalty, advantage estimation, training stability and sample efficiency

### 2. Design rewards

- Build reward models, RLVR (verifiable rewards) and LLM-as-a-Judge pipelines
- Detect, analyze and address reward hacking and reward over-optimization

### 3. Manage training data quality

- Generate synthetic data and manage data quality: mixture optimization, difficulty control, deduplication and benchmark contamination checks
- Generate and filter preference and synthetic data

### 4. Build evaluation in-house

- Design new internal evaluation sets that correlate with product quality
- Design and build our evaluation platform in-house, and design human evaluation, A/B tests and annotation guidelines

We're happy to go into more detail during the intro call and interviews.

## Why this role

- **Own the core of what makes the model smart.** You'll own the algorithms, rewards and data that optimize general-purpose LLMs for our use cases, and you'll be responsible for post-training quality. You won't just use a platform; you'll design the model's intelligence itself.
- **Build a second business pillar from scratch.** We plan to offer the performance gained through post-training as an API and grow it into a second pillar of the business. Your work spans product optimization all the way to a new business.
- **Run cutting-edge methods in production.** You'll apply top-lab methods, such as online RL like GRPO, long CoT and reasoning, and agentic post-training, directly to a product that major enterprises run in production.

## Tech stack

- **Languages & frameworks:** Python, PyTorch
- **Training methods:** SFT, DPO, KTO, ORPO, SimPO, PPO, GRPO, RLOO
- **Rewards & evaluation:** Reward models, RLVR (verifiable rewards), LLM-as-a-Judge
- **RL & distributed training:** verl, OpenRLHF, TRL, FSDP, DeepSpeed, Megatron-LM
- **Rollout inference:** vLLM, SGLang
- **Experiment tracking & compute:** Weights & Biases, etc.; Slurm, Kubernetes

## Our product

We build the Recho AI Voice Platform, which delivers voice conversations natural enough to be hard to tell apart from a human. We also deploy and operate Voice AI Agents for large enterprises.

Our edge is a platform for building and improving high-quality agents quickly. It captures industry know-how and turns user feedback into a fast, continuous improvement loop. Our agents now handle complex, large-scale contact center operations in finance, manufacturing and the public sector. In some deployments, they've resolved every call without handing off to a human agent.

## Hiring process

Intro call → Case assignment & first interview → Paid work trial* → Final interview → Offer meeting

\*The work trial is 1–2 consecutive days at our Tokyo office, working on real tasks alongside the team, and it's paid. It's a chance for both sides to check fit and get a feel for the work.

- **If you're based outside Japan,** we'll agree on the format together. We won't ask you to travel to Japan just for this step.
- If your schedule or your current employer's side-work policy makes the trial difficult, just let us know.
- We may also ask for references.

## About Recho

Recho develops foundation models for customer-support AI agents and also deploys them for clients, all within one organization. Our core strength is voice AI technology we built entirely in-house, which resolves the industry's long-standing trade-off between quality and cost.

We've closed a Series A of approximately ¥700M and are rapidly rolling out to demanding production environments at major companies such as SBI Shinsei Bank and KDDI.

## Learn more

- [Corporate website](https://recho-ai.com/)
- [Team interviews (note, in Japanese)](https://note.com/recho_ai)
- [Company deck](https://recruit.recho-ai.com/)
- [Case study: Partnership with KDDI and Altius Link (Japanese)](https://prtimes.jp/main/html/rd/p/000000021.000159800.html)
- [Case study: SBI Shinsei Bank (Japanese)](https://mainichi.jp/articles/20260130/k00/00m/020/275000c)
- [2-minute voice demo](https://recruit.recho-ai.com/#2f276fb799f480d5bba7d5784d6ad31e) — give it a listen!

必須スキル

## In short

You'll make Recho's AI models smarter for our use cases through post-training. You'll design the training methods, the reward design that "grades" the model, and the training data yourself, and you'll own the model's intelligence itself. Your job is to optimize general-purpose LLMs for our use cases, and down the line, we plan to offer that performance externally as an API business.

- **Team language:** English (Japanese not required)
- **Salary:** ¥10M–¥20M per year, plus stock options
- **Location:** Tokyo (Hanzomon), hybrid. Candidates based outside Japan are welcome. We offer visa sponsorship and relocation support, and we're open to discussing fully remote arrangements.

## You might be a fit if you are…

- An ML engineer or researcher who has worked deeply on LLM training, especially post-training
- Someone who has applied SFT, preference optimization or RLHF to a production model and shipped it
- Someone with a CS or math background (MS/PhD, or equivalent industry experience) and a track record of conference publications or open-source work

## About the role

At Recho, we don't use general-purpose LLMs as they are. We optimize them for our use cases through post-training and build them deep into our product. Your core mission is to design, implement and run training methods such as SFT, preference optimization and reinforcement learning (RL), and to own training quality for post-training of a single model.

You'll work at the core of what makes the model smart. That includes reward design (reward models, RLVR, LLM-as-a-Judge), designing training data quality and mixture ratios, and improving the post-training algorithms themselves (loss functions, KL penalty, advantage estimation, training stability).

We also plan to offer the performance we gain here externally as an API and grow it into a second pillar of our business. The scope includes post-training for agentic use cases such as long CoT and reasoning, tool use and function calling.

## What this role is *not*

- Not an on-call or SRE role. SLA management, incident recovery and infrastructure maintenance for online services are not the focus.
- GPU cluster operations and general SRE/DevOps are handled by a separate team.
- Building the infrastructure that runs training and inference (rollout systems, weight sync, GPU allocation) belongs to our RL Infrastructure Engineer role. You'll own the algorithms, rewards and data, and partner with that team.
- Pre-training from scratch is not the main job. The focus is post-training.

## What you'll do

### 1. Design, implement and run post-training

- Design, implement and run SFT, preference optimization (DPO, KTO, ORPO, SimPO, etc.) and online RL (PPO, GRPO, RLOO, etc.)
- Post-training for long CoT and reasoning, tool use, function calling and agentic use cases
- Improve post-training algorithms: loss functions, KL penalty, advantage estimation, training stability and sample efficiency

### 2. Design rewards

- Build reward models, RLVR (verifiable rewards) and LLM-as-a-Judge pipelines
- Detect, analyze and address reward hacking and reward over-optimization

### 3. Manage training data quality

- Generate synthetic data and manage data quality: mixture optimization, difficulty control, deduplication and benchmark contamination checks
- Generate and filter preference and synthetic data

### 4. Build evaluation in-house

- Design new internal evaluation sets that correlate with product quality
- Design and build our evaluation platform in-house, and design human evaluation, A/B tests and annotation guidelines

We're happy to go into more detail during the intro call and interviews.

## Why this role

- **Own the core of what makes the model smart.** You'll own the algorithms, rewards and data that optimize general-purpose LLMs for our use cases, and you'll be responsible for post-training quality. You won't just use a platform; you'll design the model's intelligence itself.
- **Build a second business pillar from scratch.** We plan to offer the performance gained through post-training as an API and grow it into a second pillar of the business. Your work spans product optimization all the way to a new business.
- **Run cutting-edge methods in production.** You'll apply top-lab methods, such as online RL like GRPO, long CoT and reasoning, and agentic post-training, directly to a product that major enterprises run in production.

## Tech stack

- **Languages & frameworks:** Python, PyTorch
- **Training methods:** SFT, DPO, KTO, ORPO, SimPO, PPO, GRPO, RLOO
- **Rewards & evaluation:** Reward models, RLVR (verifiable rewards), LLM-as-a-Judge
- **RL & distributed training:** verl, OpenRLHF, TRL, FSDP, DeepSpeed, Megatron-LM
- **Rollout inference:** vLLM, SGLang
- **Experiment tracking & compute:** Weights & Biases, etc.; Slurm, Kubernetes

## Our product

We build the Recho AI Voice Platform, which delivers voice conversations natural enough to be hard to tell apart from a human. We also deploy and operate Voice AI Agents for large enterprises.

Our edge is a platform for building and improving high-quality agents quickly. It captures industry know-how and turns user feedback into a fast, continuous improvement loop. Our agents now handle complex, large-scale contact center operations in finance, manufacturing and the public sector. In some deployments, they've resolved every call without handing off to a human agent.

## Hiring process

Intro call → Case assignment & first interview → Paid work trial* → Final interview → Offer meeting

\*The work trial is 1–2 consecutive days at our Tokyo office, working on real tasks alongside the team, and it's paid. It's a chance for both sides to check fit and get a feel for the work.

- **If you're based outside Japan,** we'll agree on the format together. We won't ask you to travel to Japan just for this step.
- If your schedule or your current employer's side-work policy makes the trial difficult, just let us know.
- We may also ask for references.

## About Recho

Recho develops foundation models for customer-support AI agents and also deploys them for clients, all within one organization. Our core strength is voice AI technology we built entirely in-house, which resolves the industry's long-standing trade-off between quality and cost.

We've closed a Series A of approximately ¥700M and are rapidly rolling out to demanding production environments at major companies such as SBI Shinsei Bank and KDDI.

## Learn more

- [Corporate website](https://recho-ai.com/)
- [Team interviews (note, in Japanese)](https://note.com/recho_ai)
- [Company deck](https://recruit.recho-ai.com/)
- [Case study: Partnership with KDDI and Altius Link (Japanese)](https://prtimes.jp/main/html/rd/p/000000021.000159800.html)
- [Case study: SBI Shinsei Bank (Japanese)](https://mainichi.jp/articles/20260130/k00/00m/020/275000c)
- [2-minute voice demo](https://recruit.recho-ai.com/#2f276fb799f480d5bba7d5784d6ad31e) — give it a listen!

歓迎スキル

## Nice-to-haves

**Broader models & methods**

- Post-training experience with multimodal models (image, audio)
- Experience with Japanese-specialized models, tokenizer design or continued pre-training
- Knowledge of inference optimization (quantization, speculative decoding, KV cache optimization)

**Large-scale operations & track record**

- Experience stabilizing training and handling failures on large clusters
- Publications at major conferences (NeurIPS, ICML, ICLR, ACL, etc.), or a notable track record in open source or technical blogging

**Languages**

- Japanese or Chinese. Our team works in English, but Japanese (the company's working language) or Chinese (spoken by many of our colleagues) makes cross-team collaboration even smoother.

求める人物像

## What we look for

- **Finds root causes with data:** You go beyond benchmark numbers. You pinpoint the causes of failure patterns through data and experiments, and turn them into reward and data improvements.
- **Improves algorithms yourself:** You don't just use existing methods as they are. You dig into loss functions and reward design to make them better.
- **Works backward from product quality:** You define evaluations that correlate with product quality, and design training from there.
- **Bridges research and production:** You take cutting-edge methods all the way to a production model release.

## Our values

These are the values our team relies on to deliver Recho's value as fast as possible.

- **Exceed Expectations:** We keep exceeding the expectations of customers and teammates by delivering both speed and quality.
- **Team-First:** Each of us takes professional ownership, and we maximize the team's results, not individual ones.
- **Continuous Feedback:** We engage seriously and speak candidly for the sake of results. The harder something is to say, the more we say it with honesty, respect and care.
- **Earn Trust:** Trust is the foundation of every collaboration and every challenge. We act ethically and keep personal and company matters separate. Trust takes time to build and a moment to lose.

応募概要

給与

## Salary

Compensation is based on your current compensation, skills and experience.

- **Annual salary:** ¥10M–¥20M
- **Salary review:** Once a year, based on your contribution and company performance
- **Stock option plan**

勤務地

WeWork Hanzomon (Hanzomon PREX North, 2-3-2 Kojimachi, Chiyoda-ku, Tokyo)
Hybrid: mostly in the office, with some remote work. For candidates based outside Japan, remote arrangements are open to discussion.

雇用形態

Employment type: Full-time, permanent. Starting with a paid contract engagement first is also an option.

勤務体系

## Working hours

- **Discretionary work system** (professional type under Japanese labor law)
- **Deemed working hours:** 9 hours/day
- Start and end times are up to you. As a general guideline, the team's core working window is 10:00–19:00, adjusted as work requires.

## Scope of duties and work location

This disclosure is required under Japanese labor law.

- **Duties:** Design and development of LLM post-training (training algorithms, rewards and data) at hire; subject to change as determined by the company
- **Work location:** WeWork Hanzomon at hire (some remote work possible); subject to change as determined by the company

## Holidays & leave

Weekends, Japanese public holidays, year-end/New Year holidays (Dec 29–Jan 3), special leave, and paid annual leave (10 days in the first year)

試用期間

Probation period: 3 months, with no change in terms

福利厚生

**Insurance**

- Full Japanese social insurance (health, pension, employment)
- Commuting allowance (up to ¥25,000/month)

**Office**

- WeWork Hanzomon, 2 minutes from Hanzomon Station, with a dedicated floor, focus booths and meeting rooms
- Free drinks, including coffee, soft drinks and alcohol
- High-quality office chairs
- MacBook Air and external monitor provided

**Productivity**

We build AI for our customers, so we work AI-native ourselves.

- **AI tools support**
- Engineering roles: Top-tier plans for Claude Code and Codex
- Business & PM roles: Team plans that let you share context across your team
- Amazon Business account for work-related books and equipment

**Team & communication**

Beyond project meetings and day-to-day conversations on Slack, we regularly set aside time for the whole company to share progress, discuss it together and get to know each other.

- **Monday Kickoff:** Every Monday, we share everything from work updates to little things going on in our lives.
- **Monthly All-Team Meeting:** On the first Friday of each month, each team shares its results from the previous month. Afterward, we get together over food.
- **All Hands:** Twice a year, we share company direction and our mid- to long-term vision, bringing the whole organization together.

**Smoking**

- Indoor smoking prohibited; outdoor smoking area available

Demand for ML Engineer roles

New ML Engineer postings at the employers we follow are down 4% over the last 6 weeks compared with the 6 before.

Weekly new ML Engineer postings at the same employers, from the week of August 17 to the week of November 9. The fewest in a week was 508, the most 899, and the latest week had 508.
August 17Last week

Each bar is one week of new postings. The darkest bars are the last 6 weeks.

Counted from the hiring pages we’ve followed for at least five weeks, so employers we add don’t look like growth. Updated weekly.

About the role

We file this job under ML Engineer, by the work the posting describes.

ML engineers put machine learning models into products. They write the code that trains, ships, serves and monitors models so a recommendation or prediction works for real users.

Postings ask for strong Python and software engineering, a framework such as PyTorch, cloud services, and more and more often experience with large language models.

A data scientist often works out which model to build; an ML engineer makes it run reliably in production.

US government figures for computer and information research scientists

Median yearly pay, May 2025
$140,300
Expected change, 2025 to 2035
21.8% more jobsagainst 3.5% for all jobs

The government has no code for ML engineers, so these figures are for the closest group, computer and information research scientists.

Source: US Bureau of Labor Statistics, Occupational Employment and Wage Statistics (May 2025) and Employment Projections (2025 to 2035). Occupation code 15-1221.

Source details

View original posting ↗

Source notes

Source excerpts

Selected passages from the saved posting. Check the full description for conditions and exceptions.

Pay
You'll make Recho's AI models smarter for our use cases through post-training. You'll design the training methods, the reward design that "grades" the model, and the training data yourself, and you'll own the model's intelligence itself. Your job is to optimize general-purpose LLMs for our use cases, and down the line, we plan to offer that performance externally as an API business. **Team language:** English (Japanese not required) - **Salary:** ¥10M–¥20M per year, plus stock options - **Location:** Tokyo (Hanzomon), hybrid. Candidates based outside Japan are welcome. We offer visa sponsorship and relocation support, and we're open to discussing fully remote arrangements. ## You might be a fit if you are…
More source context
Compensation is based on your current compensation, skills and experience. **Annual salary:** ¥10M–¥20M - **Salary review:** Once a year, based on your contribution and company performance - **Stock option plan** 勤務地
Location & working pattern

WeWork Hanzomon (Hanzomon PREX North, 2-3-2 Kojimachi, Chiyoda-ku, Tokyo) Hybrid: mostly in the office, with some remote work. For candidates based outside Japan, remote arrangements are open to discussion.

You'll make Recho's AI models smarter for our use cases through post-training. You'll design the training methods, the reward design that "grades" the model, and the training data yourself, and you'll own the model's intelligence itself. Your job is to optimize general-purpose LLMs for our use cases, and down the line, we plan to offer that performance externally as an API business. - **Team language:** English (Japanese not required) - **Salary:** ¥10M–¥20M per year, plus stock options - **Location:** Tokyo (Hanzomon), hybrid. Candidates based outside Japan are welcome. We offer visa sponsorship and relocation support, and we're open to discussing fully remote arrangements. ## You might be a fit if you are…
More source context
勤務地 WeWork Hanzomon (Hanzomon PREX North, 2-3-2 Kojimachi, Chiyoda-ku, Tokyo) Hybrid: mostly in the office, with some remote work. For candidates based outside Japan, remote arrangements are open to discussion. 雇用形態

More relevant text appears in the full description.

Work authorization
You'll make Recho's AI models smarter for our use cases through post-training. You'll design the training methods, the reward design that "grades" the model, and the training data yourself, and you'll own the model's intelligence itself. Your job is to optimize general-purpose LLMs for our use cases, and down the line, we plan to offer that performance externally as an API business. - **Team language:** English (Japanese not required) - **Salary:** ¥10M–¥20M per year, plus stock options - **Location:** Tokyo (Hanzomon), hybrid. Candidates based outside Japan are welcome. We offer visa sponsorship and relocation support, and we're open to discussing fully remote arrangements. ## You might be a fit if you are…
AI answers unavailable

We can’t review this whole description within the current limit. Read the full posting so conditions aren’t left out. Read the full posting