Staff Research Scientist - Reinforcement Learning @ Centific

Staff Research Scientist - Reinforcement Learning at Centific. Location: United States. Role: designing environments, post-training agents, building pipelines Requirements: 7+ years ML/AI research or engineering (3+ at senior/staff), 5+ years hands-on RL with production deployments, 3+ years LLM post-training (RLHF/DPO/GRPO/PPO), strong Python and pipeline engineering, Gymnasium and reward engineering experience. Category: Research and Development (R&D) Seniority: Senior Level Tools: Python, Gymnasium, TRL, veRL, OpenRLHF, SkyRL Commitment: Full Time Workplace: Remote Languages: English