About this role
Member of Technical Staff — RL Research at Nuance Labs. Location: Seattle, Washington, United States. Role: building stack, developing methods, scaling systems Requirements: Hands-on experience with RL/RLHF/post-training for foundation models, building large-scale training/inference pipelines, familiarity with rollout generation, reward modeling, policy optimization, evaluation, and strong software engineering. Category: Research and Development (R&D) Seniority: Senior Level Tools: verl, ms-swift, OpenRLHF, vLLM Commitment: Full Time Workplace: Onsite Languages: English