Research Engineer (Reinforcement Learning)

Location

Location: Redwood City, CA (Hybrid)

Company

hirify.global builds unified general intelligence with a focus on multimodality beyond language models, emphasizing vision and physical world operation.

What you will do

• Design, build, and scale distributed RL post-training systems across thousands of GPUs.
• Develop high-throughput rollout generation integrating inference engines and asynchronous schemes.
• Create RL environments for agentic, multi-step tasks with sandboxed execution and multimodal interaction.
• Build reward infrastructure including verifiable rewards, reward-model serving, and defenses against reward hacking.
• Develop evaluation, monitoring, and debugging tools to maintain stability of large RL runs.
• Advance training efficiency and implement new post-training ideas in production.

Requirements

• Location: Redwood City, CA with hybrid work format.
• Hands-on experience with post-training LLMs using RL at scale (PPO/GRPO-family, RLHF, RLVR).
• Extensive distributed PyTorch training and parallelism for foundation models.
• Experience building RL environments, reward functions, verifiers, and evaluation harnesses for LLM agents.
• Familiarity with RL post-training frameworks and rollout inference engines.
• Strong understanding of GPU clusters, networking, and communication libraries under mixed workloads.

Nice to have

• Experience running RL training across 100+ GPUs with asynchronous or disaggregated architectures.
• Containerization and orchestration skills (Kubernetes, Ray) for large environment fleets.
• Research or open-source contributions in RL for LLMs.