First Monday
Jobs
Jobs open to youOnly jobs that can hire where you liveA CV for each jobWritten from your record, every line checkedMemoryIt remembers, so you don’t repeat yourselfInterview helpResearch, prep and hints only you seeWatch how it works0:28
FAQDocsUse in AI, Free
Your countryNorth AmericaEuropeAsia-PacificLatin AmericaNot on the list? Tell us where you liveRequest early accessEarly access
First Monday

Remote jobs that can actually hire you.

Beta formacOSWindows

Jobs

Jobs open to you in CanadaRemote jobs in the USRemote jobs in PolandRemote jobs in the UKRemote jobs in CanadaRemote jobs in Mexico

Product

Jobs open to youA CV for each jobMemoryInterview helpHow it works

Company

FAQContact

Legal

Privacy PolicyTerms & Conditions
Jobs
Jobs open to you in CanadaRemote jobs in the USRemote jobs in PolandRemote jobs in the UKRemote jobs in CanadaRemote jobs in Mexico
Product
Jobs open to youA CV for each jobMemoryInterview helpHow it works
Company
FAQContact
Legal
Privacy PolicyTerms & Conditions
Remote jobs by country
United StatesPolandUnited KingdomCanadaMexicoBrazilGermanySpainPortugalIrelandNetherlandsIndiaSwedenBelgiumAustriaDenmarkFinlandSwitzerlandNorwayAustraliaNew Zealand

Remote jobs by country

United StatesPolandUnited KingdomCanadaMexicoBrazilGermanySpainPortugalIrelandNetherlandsIndiaSwedenBelgiumAustriaDenmarkFinlandSwitzerlandNorwayAustraliaNew Zealand
© 2026 First MondayNo tracking cookies. Anonymous page statistics only.
First Monday
Jobs/Data and AI/Research Scientist / Engineer – Reinforcement Learning Infrastructure

Research Scientist / Engineer – Reinforcement Learning Infrastructure

Luma

Remote · EUData and AIPosted October 8, 2026
Open to people in 11 countriesApply for this job Write my CV for this job Early access
Pay
Not stated
Required
vLLM, SGLang, PyTorch, FSDP, veRL, OpenRLHF, TRL, Ray, NCCL, MPI
Nice to have
Kubernetes, Ray
Posted
October 8, 2026
Company
Luma

Who it can hire

We read the post for each of the 21 countries we cover.

  • Open to people in Ireland, Germany, the Netherlands, Belgium, Austria, Sweden, Denmark, Finland, Poland, Spain and Portugal

    The employer lists this job as remote there: “Remote, EU”.

  • Not open to people in the other 10 countries we cover, as far as the post says.

The job post

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.

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.

First Monday isn’t the employer or a recruiter and isn’t affiliated with Luma. Details may have changed since; confirm with the employer before you apply.

Open to people in 11 countriesApply for this job Write my CV for this job Early access
Pay
Not stated
Required
vLLM, SGLang, PyTorch, FSDP, veRL, OpenRLHF, TRL, Ray, NCCL, MPI
Nice to have
Kubernetes, Ray
Posted
October 8, 2026
Company
Luma

Similar jobs open to people in Ireland

Research Engineer / Scientist, Agentic RL Post-Trainingellamind · Bremen · BerlinMachine Learning Engineer — Inference OptimizationFeatherless AI · Remote · WorldwideMMember of Technical Staff, Model Training (post-training research)Micro1 · Remote · WorldwideAI Engineer – Marketing & GTM SystemsRwazi · Remote · Worldwide
First Monday

Get jobs like this every Monday.

One email a week with new remote jobs open to people in Canada. Free, and one click to unsubscribe. Privacy Policy

Or request early access to the app
Apply for this job