Luma
Research Scientist / Engineer – Reinforcement Learning Infrastructure
- Location
- Portola Valley, San Mateo County
- Employment
- Full Time
Job summary
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 …
SalaryCheck the source listing for salary
General interview preparation
General preparation guidance from MiPrep; these interview stages are not confirmed for this job.
- Recruiter phone screen - typically 20-40 min
- Technical screen - 1 coding problem or take-home; format varies by company
- Onsite / virtual loop - typically 4-6 rounds over 2-3 weeks; exact split of coding, systems design, and behavioral varies by role and location