Back to jobs

LLM Inference Systems Engineer

Menlo Park, California, United States

Live, first seen by us 45 days ago
Pay
Pay not listedSimilar roles state $90K–$150K
Work setting
On-site — work setting source
Work setup in the employer’s posting: On-site
From the employer’s posting
Employment
Full-time — employment source
Employment type in the employer’s posting: FullTime
From the employer’s posting

What you’ll work on

Full posting

We’re seeking an inference systems engineer to build the distributed serving and high-performance networking layer behind our large language models.

  • Design, implement, and operate disaggregated LLM serving architectures, including independent prefill and decode pools, KV-cache transfer, routing, batching, and failure recovery.

  • Optimize multi-node inference across modern GPU systems using NVLink, NVSwitch, NVLS, InfiniBand, RoCEv2, GPUDirect RDMA, NCCL, UCX, and related communication paths.

  • Build and tune serving systems using SGLang, vLLM, NVIDIA Dynamo, TensorRT-LLM, or comparable frameworks.

From the employer’s posting
We’re seeking an inference systems engineer to build the distributed serving and high-performance networking layer behind our large language models. You will own the path from model server to GPU fabric: prefill/decode disaggregation, KV-cache transfer, multi-node execution, and the observability and benchmarks needed to make those systems reliable in production. This role sits in the Inference team within the company’s Model team and partners closely with Model, Infrastructure, and Application engineering.
WHAT YOU’LL DO Design, implement, and operate disaggregated LLM serving architectures, including independent prefill and decode pools, KV-cache transfer, routing, batching, and failure recovery. Optimize multi-node inference across modern GPU systems using NVLink, NVSwitch, NVLS, InfiniBand, RoCEv2, GPUDirect RDMA, NCCL, UCX, and related communication paths.
Design, implement, and operate disaggregated LLM serving architectures, including independent prefill and decode pools, KV-cache transfer, routing, batching, and failure recovery. Optimize multi-node inference across modern GPU systems using NVLink, NVSwitch, NVLS, InfiniBand, RoCEv2, GPUDirect RDMA, NCCL, UCX, and related communication paths. Build and tune serving systems using SGLang, vLLM, NVIDIA Dynamo, TensorRT-LLM, or comparable frameworks.
Optimize multi-node inference across modern GPU systems using NVLink, NVSwitch, NVLS, InfiniBand, RoCEv2, GPUDirect RDMA, NCCL, UCX, and related communication paths. Build and tune serving systems using SGLang, vLLM, NVIDIA Dynamo, TensorRT-LLM, or comparable frameworks. Profile end-to-end performance across compute, memory, network, and storage; improve time to first token, inter-token latency, throughput, tail latency, and cost per token.

Before you apply

Employer’s visa record
4 H-1B petitions approved in fiscal 2024 and 2025For the employer as a whole. This posting doesn’t say whether the role is sponsored. US Citizenship and Immigration Services.

What you’ll bring

All qualifications

Core experience

  • Strong understanding of LLM inference, including tensor/pipeline/data parallelism, continuous batching, KV-cache management, and prefill/decode behavior.
  • Experience with NVLS, SHARP, GPUDirect RDMA, UCX, RDMA congestion control, or GPU-cluster topology optimization.
  • Hands-on experience with GPU communication and networking technologies such as NCCL, NVLink/NVSwitch, InfiniBand, RoCE, RDMA, UCX, or equivalent systems.
  • Experience with speculative decoding, multi-LoRA serving, quantization, or cache-aware routing.
  • Strong Python skills and working proficiency in C++ or another systems language.
  • Experience benchmarking new GPU platforms and turning results into production architecture decisions.
Qualification wording
Strong understanding of LLM inference, including tensor/pipeline/data parallelism, continuous batching, KV-cache management, and prefill/decode behavior.
Experience with NVLS, SHARP, GPUDirect RDMA, UCX, RDMA congestion control, or GPU-cluster topology optimization.
Hands-on experience with GPU communication and networking technologies such as NCCL, NVLink/NVSwitch, InfiniBand, RoCE, RDMA, UCX, or equivalent systems.
Experience with speculative decoding, multi-LoRA serving, quantization, or cache-aware routing.
Strong Python skills and working proficiency in C++ or another systems language.
Experience benchmarking new GPU platforms and turning results into production architecture decisions.
Education & alternatives
- Clear written and verbal communication across research, infrastructure, and product-facing teams. - Master's or PhD Required Nice-to-Have:
Apply at hippocratic%20ai

Posting record

Report an error
Status in our records
Live
First seen by us
Oct 7, 202645 days ago
Recorded sightings
39
Last seen by us
Nov 21, 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

Pay

$90K–$150K is typical

The middle half of what similar US postings state. This one doesn’t list pay.

From 23,355 postings in the last year. Stated ranges, not salaries paid.

Time since we first saw it

Day 45

Similar jobs usually come down between day 9 and day 60.

From 40,910 similar postings that came down. Coming down is not always a hire.

hippocratic%20ai is hiring

7 open jobs

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

  • Hiring has slowed
  • 14% of open jobs were reposted
Hiring record

See how this role fits your experience

Add your resume and we’ll mark which of these tools you already use, and point out anything in the posting that could rule you out.

  • C++
  • Python
  • Kubernetes
Where the posting names them
- Hands-on experience with GPU communication and networking technologies such as NCCL, NVLink/NVSwitch, InfiniBand, RoCE, RDMA, UCX, or equivalent systems. - Strong Python skills and working proficiency in C++ or another systems language. - Ability to profile and debug performance across application, runtime, kernel, network, and infrastructure layers.
- Develop repeatable benchmark and capacity-planning workflows across model architectures, GPU types, parallelism strategies, and concurrency levels. - Productionize serving on Kubernetes with health checks, autoscaling, safe rollouts, metrics, tracing, and actionable diagnostics. - Diagnose complex distributed failures such as collective timeouts, topology mismatches, packet loss, congestion, KV-transfer stalls, GPU OOMs, and uneven load.
- Ability to profile and debug performance across application, runtime, kernel, network, and infrastructure layers. - Experience deploying production workloads on Kubernetes and operating them with clear reliability and observability standards. - Clear written and verbal communication across research, infrastructure, and product-facing teams.

Your next step

Complete your application on jobs.ashbyhq.com. The employer’s form will show what is required.

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 ↗

ABOUT THE ROLE

We’re seeking an inference systems engineer to build the distributed serving and high-performance networking layer behind our large language models. You will own the path from model server to GPU fabric: prefill/decode disaggregation, KV-cache transfer, multi-node execution, and the observability and benchmarks needed to make those systems reliable in production. This role sits in the Inference team within the company’s Model team and partners closely with Model, Infrastructure, and Application engineering.

WHAT YOU’LL DO

  • Design, implement, and operate disaggregated LLM serving architectures, including independent prefill and decode pools, KV-cache transfer, routing, batching, and failure recovery.

  • Optimize multi-node inference across modern GPU systems using NVLink, NVSwitch, NVLS, InfiniBand, RoCEv2, GPUDirect RDMA, NCCL, UCX, and related communication paths.

  • Build and tune serving systems using SGLang, vLLM, NVIDIA Dynamo, TensorRT-LLM, or comparable frameworks.

  • Profile end-to-end performance across compute, memory, network, and storage; improve time to first token, inter-token latency, throughput, tail latency, and cost per token.

  • Develop repeatable benchmark and capacity-planning workflows across model architectures, GPU types, parallelism strategies, and concurrency levels.

  • Productionize serving on Kubernetes with health checks, autoscaling, safe rollouts, metrics, tracing, and actionable diagnostics.

  • Diagnose complex distributed failures such as collective timeouts, topology mismatches, packet loss, congestion, KV-transfer stalls, GPU OOMs, and uneven load.

  • Partner with model researchers and platform engineers to launch new models, serving features, and hardware generations safely.

LOCATION REQUIREMENT

We believe the best ideas happen together. To support fast collaboration and a strong team culture, this role is expected to be in our Menlo Park office five days a week, unless otherwise specified.

WHAT YOU BRING

Must-Have:

  • Production experience building or operating distributed systems, high-performance computing systems, or large-scale ML inference platforms.

  • Strong understanding of LLM inference, including tensor/pipeline/data parallelism, continuous batching, KV-cache management, and prefill/decode behavior.

  • Hands-on experience with GPU communication and networking technologies such as NCCL, NVLink/NVSwitch, InfiniBand, RoCE, RDMA, UCX, or equivalent systems.

  • Strong Python skills and working proficiency in C++ or another systems language.

  • Ability to profile and debug performance across application, runtime, kernel, network, and infrastructure layers.

  • Experience deploying production workloads on Kubernetes and operating them with clear reliability and observability standards.

  • Clear written and verbal communication across research, infrastructure, and product-facing teams.

  • Master's or PhD Required

Nice-to-Have:

  • Direct experience with disaggregated serving, KV-cache transfer, NVIDIA Dynamo/NIXL, SGLang, vLLM, or TensorRT-LLM.

  • Experience with NVLS, SHARP, GPUDirect RDMA, UCX, RDMA congestion control, or GPU-cluster topology optimization.

  • CUDA, Triton, custom kernel, or low-level GPU performance experience.

  • Experience with speculative decoding, multi-LoRA serving, quantization, or cache-aware routing.

  • Contributions to open-source inference, networking, or distributed-systems projects.

  • Experience benchmarking new GPU platforms and turning results into production architecture decisions.

REFERENCES

Why Join Hippocratic AI

Reinvent healthcare with AI that puts safety first. We’re building the world’s first healthcare‑only, safety‑focused LLM — a breakthrough platform designed to transform patient outcomes at a global scale. This is category creation.

Work with the people shaping the future. Hippocratic AI was co‑founded by CEO Munjal Shah and a team of physicians, hospital leaders, AI pioneers, and researchers from institutions like El Camino Health, Johns Hopkins, Washington University in St. Louis, Stanford, Google, Meta, Microsoft, and NVIDIA.

Backed by the world’s leading healthcare and AI investors. We recently raised a $126M Series C at a $3.5B valuation, led by Avenir Growth, bringing total funding to $404M with participation from CapitalG, General Catalyst, a16z, Kleiner Perkins, Premji Invest, UHS, Cincinnati Children’s, WellSpan Health, John Doerr, Rick Klausner, and others.

Build alongside the best in healthcare and AI. Join experts who’ve spent their careers improving care, advancing science, and building world‑changing technologies — ensuring our platform is powerful, trusted, and truly transformative.

Equal Opportunity

Hippocratic AI is an equal opportunity employer. We do not discriminate on the basis of race, color, religion, national origin, sex, age, disability, sexual orientation, gender identity or expression, genetic information, military or veteran status, or any other characteristic protected by applicable law. We are committed to building a team that reflects the patients we serve. We actively encourage applications from candidates of all backgrounds. If you require accommodations during the hiring process, please contact people@hippocraticai.com.

Please be aware of recruitment scams impersonating Hippocratic AI. All recruiting communication will come from @hippocraticai.com email addresses. We will never request payment or sensitive personal information during the hiring process.

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

Menlo Park, California, United States

Working pattern and location restrictions need checking in the full posting.

Work authorization

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

Find answers in the posting

AI
How answers work

AI selects complete passages from this posting. Check them for conditions and exceptions.

Uses this posting and your question. No profile needed.