Staff Agent Post-Training ML Research Engineer (RLHF/Agents)

Scale; San Francisco, New York (CA, NY); On-site; USD 265,000 - 331,000; Full time

Benefits offered by this job

Health, dental and vision coverage

Retirement benefits

Learning and development stipend

Generous PTO

Commuter stipend

Job summary

Scale is hiring a Staff Machine Learning Research Engineer, Post-training, for Enterprise GenAI in San Francisco. The role focuses on building an Agent RL training platform and integrating cutting-edge research into the training stack to deploy high‑performing enterprise agents.

You will train state-of-the-art models, explore post-training methods like RLHF/RLVR, and design multi-agent learning solutions. The role requires deep research experience and a PhD or MS in CS or a related field.

Qualifications

• 5+ years of LLM training in a production environment.
• Experience with post-training methods like RLHF/RLVR and related algorithms like PPO/GRPO.
• Publications in top conferences such as NEURIPS, ICLR, or ICML within the last two years.

Responsibilities

• Train state-of-the-art models for enterprise use.
• Research cutting-edge algorithms to integrate into the training stack.
• Design solutions for multi-agent systems to learn from rewards.

Skills

LLM training

Post-training methods RLHF/RLVR

PPO/GRPO algorithms

Research publications

Education

PhD or MS in CS or related field

Job description

Scale is hiring a Staff Machine Learning Research Engineer, Post-training, for Enterprise GenAI in San Francisco. The role focuses on building an Agent RL training platform and integrating cutting-edge research into the training stack to deploy high‑performing enterprise agents.

You will train state-of-the-art models, explore post-training methods like RLHF/RLVR, and design multi-agent learning solutions. The role requires deep research experience and a PhD or MS in CS or a related field.