Back to jobs

AI engineer

Paris · Barcelona · London · Paris, France

Open 3 months, first seen by us 99 days ago
Pay
Pay not listed
Work setting
Hybrid — work setting source
Location type: Hybrid
From the employer’s posting
Employment
Full-time — employment source
Employment type: Full-time
From the employer’s posting
Team
Product & tech — team source
Department: Product & tech
From the employer’s posting

What you’ll bring

All qualifications

Core experience

  • You have 8+ years' experience building and shipping software and ML systems in production
  • Python repo and TS monorepo (platform) · PostgreSQL + Prisma · AWS (Terraform) · GitHub Actions · Claude Code + Cursor · AI/agent framework: mostly Langchain ecosystem
  • 100% of our teams are equipped with the best AI agents.
Qualification wording
You have 8+ years' experience building and shipping software and ML systems in production
Python repo and TS monorepo (platform) · PostgreSQL + Prisma · AWS (Terraform) · GitHub Actions · Claude Code + Cursor · AI/agent framework: mostly Langchain ecosystem
At Lucis, AI isn't just our product, it's our engine. 100% of our teams are equipped with the best AI agents. You have carte blanche to explore and automate everything that can be, so you can focus exclusively on high-value work.

Tools in this posting

  • Python
  • AWS
  • PostgreSQL
  • Terraform
Source — Tool mentions in context
- You think in systems: prompts, retrieval, tool orchestration, evals, and failure modes are all part of the same design problem - You're hands-on with vector databases, retrieval pipelines, and LLM endpoints — Python-native, comfortable in LangChain or equivalent - You write evals before you ship, because you know that vibes-based QA doesn't work for clinical reasoning
Our current stack Python repo and TS monorepo (platform) · PostgreSQL + Prisma · AWS (Terraform) · GitHub Actions · Claude Code + Cursor · AI/agent framework: mostly Langchain ecosystem The process

Posting record

Report an error

Open 3 monthsWe first saw this posting 99 days ago and it is still up. Roles open this long are often slow to fill or kept open to collect applications.

Status in our records
Live
First seen by us
Aug 12, 202699 days ago
Recorded sightings
57
Last seen by us
Nov 20, 2026
Employer says posted
Apr 8, 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 99

Up longer than most. Similar jobs usually come down between day 1 and day 14.

From 1,255 similar postings that came down. Coming down is not always a hire.

Your next step

Check the employer’s posting for the current role and application details.

Applying through Ashby

  • No account needed. “Autofill from resume” at the top of the form fills the key fields from your file.

Already applied? Track this application

Job description

View original posting ↗

Making preventive health the default for every human in Europe

 

The mission

At Lucis, we believe healthcare should be preventive, not reactive. We’re building the OS for human longevity to help people add more healthy years to their lives. You can read more about who we are and how we work here.

 


The role

We're building AI agents that act as a doctor for preventive health — analyzing 110+ biomarkers, reasoning over clinical data, and delivering protocols that change how people age. The system works. Now we need to make it smarter, faster, and ready for millions of users.

 

As our AI Engineer, you own the reasoning engine: the agents, the retrieval pipelines, the clinical workflows, and the infrastructure that makes it all reliable in production. You work directly with our medical team to translate clinical knowledge into systems that actually behave like they understand it.

 

This isn't a research role. It's a build role. The gap between a great LLM demo and a trustworthy AI doctor is enormous — your job is to close it.

 

You could be responsible for

  • AI agent architecture — design and ship the multi-agent system behind our AI doctor: reasoning, planning, tool use, clinical citation, and safe fallback behavior

  • Retrieval & knowledge — vector infrastructure, embedding pipelines, RAG architecture over clinical literature and user health data. You know the difference between retrieval that works and retrieval that a clinician would trust

  • Data pipelines — ingestion and normalization from labs (Eurofins, Randox), wearables, and third-party partners. Clean data in, reliable inference out

  • Production reliability — LLM endpoints that reason correctly at scale, with observability, evals, and failure modes you've thought through before they happen

  • Medical collaboration — translate complex clinical requirements into agent workflows, working side by side with our medical advisors. You don't need to be a doctor, but you need to earn their trust

 
 

About you

You’re passionate about the future of human health and want your work to help people stay healthy for longer. You move quickly from idea to execution, take full ownership of what you build, and work best with talented people who care as much as you do.

 

You thrive in fast‑moving environments, learn by doing, and value feedback as a way to continuously improve.

 

You’ll fit in well if

  • You have 8+ years' experience building and shipping software and ML systems in production

  • You've shipped AI agents in production recently — not as a side project, as the core product

  • You think in systems: prompts, retrieval, tool orchestration, evals, and failure modes are all part of the same design problem

  • You're hands-on with vector databases, retrieval pipelines, and LLM endpoints — Python-native, comfortable in LangChain or equivalent

  • You write evals before you ship, because you know that vibes-based QA doesn't work for clinical reasoning

  • You've worked with messy real-world data (health, finance, legal) and built pipelines that handle it without breaking silently

  • You're genuinely obsessed with health — you track your own biomarkers, read PubMed, or are just deeply frustrated that healthcare is still reactive

 

We might not be a fit if

  • You need a clearly defined role with stable responsibilities.

  • You prefer strategic advisory work over hands-on execution.

  • You've only worked in large, well-established companies.

  • You need perfect information before making decisions.

  • You prioritise predictable 9–5 work over mission intensity.

  • You're uncomfortable with frequent context-switching and urgent pivots.

 

Our current stack

Python repo and TS monorepo (platform) · PostgreSQL + Prisma · AWS (Terraform) · GitHub Actions · Claude Code + Cursor · AI/agent framework: mostly Langchain ecosystem

 

The process

  • Intro call (20 min): culture & role fit.

  • Technical interview (30 min)

  • At-home case study: hands-on project, delivery in 2 days.

  • Deep dive (90 min) and team chat (on-site)

  • Reference calls

 

How we work

We work together from our Paris hub. We’re passionate about what we’re building and believe the fastest way to create something exceptional is side by side. We’re open to relocation support for the right individuals, and we welcome missionaries who travel to work with us in Paris on a regular basis.

 
  • Rigor without ego: Audits, science, and code all deserve the same high bar.

  • Radical ownership: Feedback loops are short; everyone contributes to building the best version of Lucis.

  • Velocity over perfection: We ship daily and prefer a good decision today over a perfect one next week.

At Lucis, AI isn't just our product, it's our engine. 100% of our teams are equipped with the best AI agents. You have carte blanche to explore and automate everything that can be, so you can focus exclusively on high-value work.

About the role

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

AI engineers build products on top of AI models that already exist, most often large language models: they connect a model to a company's data and tools and ship the assistants, agents and search features people use.

Postings ask for strong Python or TypeScript, experience with model APIs, retrieval and agent frameworks, and ways to test whether the model's answers are good enough.

An ML engineer trains and serves models; an AI engineer usually starts from a model someone else trained and builds the product around it, though titles often mix the two.

Source details

View original posting ↗

Source notes

Source excerpts

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

Pay

No pay amount identified in the saved description.

Location & working pattern

Paris, France

- At-home case study: hands-on project, delivery in 2 days. - Deep dive (90 min) and team chat (on-site) - Reference calls
Work authorization

No clear work-authorization passage found. Eligibility is unconfirmed.

AI answers unavailable

We couldn’t identify enough role detail in this saved description to support an AI answer. Read the full posting