Machine Learning Engineer jobs

Research Scientist / Engineer – Reinforcement Learning Infrastructure

LumaRedwood City, CA +3 placesFull-timeHybrid

$195k–$395k/yr listed by the employer

Key facts

Schedule
Days
Where
Redwood City, CA · United States · New York, NY · Seattle, WA · hybrid

Looks real. 2 things to check before you apply.

On Luma’s own careers site (Ashby), checked open today.

  • To check: Posted by the employer 4 months agoLong-open jobs are sometimes already filled. Ask when they plan to hire.
  • To check: Wide pay range: top of the range is 2.03× the bottomAsk what the job pays at your level before you interview.
  • Checked: On the company's own careers siteAshby board
  • Checked: Checked open todayAshby board
  • Checked: Pay listedJob posting
  • Checked: No reposts foundAshby board
  • Trust score 90 / 100 · Strong
See all 7 checksShow fewer
How we check

What you’ll do

  • Build and scale distributed RL post-training systems across trainer, rollout, environment, and reward workloads.
  • Develop high-throughput rollout generation using inference engines, weight synchronization, and asynchronous or off-policy methods.
  • Create scalable environments for agentic tasks and build reward, verification, and reward-model infrastructure.
  • Develop evaluation, monitoring, and debugging tools to keep large RL runs stable, and put post-training methods into production.

Summarised from the posting by AI and can be wrong. The full description is the source.

Requirements

Experience

  • Hands-on experience post-training LLMs with RL (PPO/GRPO-family, RLHF, RLVR) at meaningful scale
  • Extensive distributed PyTorch training and parallelism (FSDP, Tensor/Pipeline/Expert Parallel) for foundation models
  • Experience building RL environments, reward functions, verifiers, or evaluation harnesses for LLM agents, including sandboxed execution and multi-turn tool use
  • Deep familiarity with RL post-training frameworks (veRL, OpenRLHF, TRL, Ray orchestration) and rollout inference engines (vLLM, SGLang)
  • Strong understanding of GPU clusters, networking, and communication libraries (NCCL, MPI) under mixed training and inference workloads
  • Running RL training across 100+ GPUs, including asynchronous or disaggregated trainer/rollout architectures (preferred)
  • Research contributions in RL for LLMs, or open-source contributions to RL training frameworks (preferred)

Skills

  • Containerization and orchestration (Kubernetes, Ray) for large environment fleets and sandboxed workloads (preferred)

Your match

Sign in and add your resume to see which of this job's requirements it shows.

Sign in to check your match

Saved to your account, encrypted. The AI that reads it doesn't keep it or train on it.

Full job description

From Luma’s careers site

You'll build the systems that make reinforcement learning work at frontier scale — coupling policy optimization with large fleets of inference workers, agentic environments, and the reward and verification systems that turn model behavior into learning signal. RL is how Luma's models go from capable to useful.

Show full descriptionShow less

RL at scale is a full-loop systems problem: training, rollout generation, environment execution, and reward computation running concurrently across thousands of GPUs, all needing to stay fast, stable, and correct together. It fits someone who has lived this — post-trained LLMs with RL, built environments and verifiers, and debugged asynchronous rollout pipelines at scale. If you haven't operated RL at real scale, this will be deep water.

What You'll Own

  • Design, build, and scale distributed RL post-training systems, orchestrating trainer, rollout, environment, and reward workloads across thousands of GPUs.
  • Build high-throughput rollout generation, integrating inference engines (vLLM, SGLang), weight synchronization, and asynchronous/off-policy schemes.
  • Design RL environments for agentic, multi-step tasks — sandboxed code execution, tool use, computer use, multimodal interaction — reproducible and scalable to millions of episodes.
  • Build reward infrastructure: verifiable/programmatic rewards, reward-model serving, LLM-as-judge pipelines, and defenses against reward hacking.
  • Develop the evaluation, monitoring, and debugging tooling that keeps large RL runs stable.
  • Advance training efficiency and stability, and turn new post-training ideas into production runs with researchers.

First 90 Days

One way the first 90 could unfold.

  • Days 1–30 — Immerse & Diagnose: Learn the current RL stack and where throughput, stability, or correctness break.
  • Days 30–60 — Ship & Validate: Improve a piece of the loop (rollout throughput, reward infra, or an environment) and prove it on a real run.
  • Days 60–90 — Scale & Systemize: Harden the full loop across thousands of GPUs and asynchronous architectures.

What You Bring

  • Hands-on experience post-training LLMs with RL (PPO/GRPO-family, RLHF, RLVR) at meaningful scale.
  • Extensive distributed PyTorch training and parallelism (FSDP, Tensor/Pipeline/Expert Parallel) for foundation models.
  • Experience building RL environments, reward functions, verifiers, or evaluation harnesses for LLM agents, including sandboxed execution and multi-turn tool use.
  • Deep familiarity with RL post-training frameworks (veRL, OpenRLHF, TRL, Ray orchestration) and rollout inference engines (vLLM, SGLang).
  • Strong understanding of GPU clusters, networking, and communication libraries (NCCL, MPI) under mixed training and inference workloads.

Nice to Have

  • Running RL training across 100+ GPUs, including asynchronous or disaggregated trainer/rollout architectures.
  • Containerization and orchestration (Kubernetes, Ray) for large environment fleets and sandboxed workloads.
  • Research contributions in RL for LLMs, or open-source contributions to RL training frameworks.

About Luma: Luma's mission is to build unified general intelligence that can generate, understand, and operate in the physical world. We believe multimodality is critical for intelligence — the next step beyond language models comes from vision. Luma is an equal opportunity employer.

Something wrong with this job? Report it · This flag looks wrong

Similar jobs nearby

AI Research Engineer III

Agility Robotics · Fremont, CA +2 places

$166k–$260k/yrFull-timeHybrid

StrongChecked open todayPosted 11 days ago

Machine Learning Engineer

Gotion, Inc. · Fremont, CA

$110k–$135k/yrFull-timeHybrid

StrongChecked open todayPosted 18 days ago

Machine Learning Engineer

Sift · San Francisco, CA +1 place

$170k–$240k/yrFull-timeHybrid

StrongChecked open todayPosted 24 days ago

See more like this