Who can apply: Only open to applicants in: California, New York, Washington.
Location as listed by the employer: “Redwood City, CA; Remote, US; New York, NY; Seattle, WA”
Apply on Lumaai's site ↗
Opens the employer's official application page.
Generate a CV for this job
Generate my CV
A CV tailored to this job's requirements in one click — boosted with testimonials from people who know your work.
About this role
Lumaai is hiring for a Research Scientist / Engineer – Reinforcement Learning Infrastructure role (full-time). See the official posting for full details.
Requirements
- 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.
Summarized from the employer's posting — check the full posting for every requirement.
New remote jobs for your state, by email.
A short digest only when there's something new. Confirm by email, unsubscribe anytime.