Research Scientist / Engineer – Reinforcement Learning Infrastructure
Core
Design, build, and scale distributed reinforcement learning post-training systems for large language models, orchestrating training, rollout, environment, and reward workloads across thousands of GPUs.
Role type
Senior IC reinforcement learning infrastructure engineer
Builds
Distributed RL post-training systems, high-throughput rollout generation, RL environments for agentic tasks, and reward infrastructure
Domain
Artificial Intelligence / Large Language Models / Reinforcement Learning
Deliverable
production ML models
Required skills
Reinforcement learning post-training (PPO/GRPO/RLHF/RLVR), distributed PyTorch training (FSDP, Tensor/Pipeline/Expert Parallel), RL environment design, reward modeling and verification, GPU cluster management, NCCL/MPI networking, vLLM/SGLang integration, Ray orchestration
Preferred skills
Asynchronous/disaggregated trainer-rollout architectures, Kubernetes orchestration, research contributions in RL for LLMs
Technologies
PyTorch, FSDP, vLLM, SGLang, Ray, Kubernetes, NCCL, MPI, veRL, OpenRLHF, TRL
