Europe Arbeitnow ·
full-timeResearch Scientist / Engineer – Reinforcement Learning Infrastructure
Lumaai · London, UK
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. Find Jobs in United Kingdom on Arbeitnow
| Role | Research Scientist / Engineer – Reinforcement Learning Infrastructure |
|---|---|
| Company | Lumaai |
| Location | London, UK |
| Type | full-time |
| Compensation | Not disclosed |
| Deadline | Rolling |
Typical process for this type of role
A general guide — the exact steps for this specific listing may vary; check the original posting for details.
- 1ApplicationSubmit your resume through the apply link.
- 2ScreeningRecruiter reviews your background against the role.
- 3AssessmentA technical test, assignment, or coding round, depending on the role.
- 4Interview(s)One or more rounds with the hiring team.
- 5OfferOffer letter with compensation and start date.
Before you apply
0/4More at Lumaai
Other jobs at Lumaai
- Software Engineer, Inference · London, UK
- Copy Of Research Scientist / Engineer – Training Infrastructure · London, UK
- Copy Of Research Scientist / Engineer – Performance Optimization · London, UK
- Director Of Customer Success [emea] · London, UK
Explore Related Placements
// similar opportunities
You might also like
Copy Of Research Scientist / Engineer – Training Infrastructure
Lumaai
You'll build the distributed systems that train Luma's large-scale multimodal models across thousands of GPUs, so researchers can focus on innovation on top of ...
Copy Of Research Scientist / Engineer – Performance Optimization
Lumaai
You'll make Luma's multimodal models fast — profiling and optimizing GPU, CPU, and accelerator code so they train efficiently and deploy at scale without sacrif...
Senior Reinforcement Learning Engineer
Gravis Robotics
Gravis Robotics is a high-growth Series A start-up backed by SoftBank, bringing Physical AI to the construction industry, turning heavy construction machines in...
AI Engineer - Reinforcement Learning (senior)
Rivr
RIVR, part of Amazon is a robotics company pioneering Physical AI through real-world doorstep delivery. Founded in 2024 as an ETH Zurich spin-off, RIVR develope...
Infrastructure Software Engineer, Apps Platform
Scale AI
Infrastructure Software Engineer, Apps Platform, London As an Infrastructure Engineer on the Apps Platform Infrastructure team, you'll help build and evolve our...
Senior Optical Research Scientist
Comind
At CoMind, we are developing a non-invasive neuromonitoring technology that will result in a new era of clinical brain monitoring. In joining us, you will be he...