About this role
Research Scientist, Safety Post Training at Scale AI. Location: San Francisco or New York. Role: Design pipelines, Develop evaluations, Collaborate policies Requirements: Three+ years in ML, post-training/RL techniques, strong communication. Category: Research and Development (R&D) Seniority: Mid Level Tools: RLHF, DPO, GRPO, Interpretability tools Commitment: Full Time Workplace: Hybrid Languages: English