Research Scientist, Safety Post Training

📋 Description

• Design and run post-training pipelines to study safety, robustness, and alignment.
• Develop interpretability-informed evaluations to reveal unsafe or undesirable behaviors.
• Collaborate with policymakers, engineers, and researchers to translate findings into safety standards, benchmarks, and best practices.

🎯 Requirements

• Commitment to safe, secure, and trustworthy AI deployments.
• Experience with post-training and RL techniques such as RLHF, DPO, GRPO.
• A track record of published ML research, particularly in generative AI.
• At least three years addressing sophisticated ML problems in research or product development.
• Strong written and verbal communication in cross-functional teams.
• Nice to have: mechanistic interpretability, probing, or adversarial evaluation of post-trained models.

🎁 Benefits

• Comprehensive health, dental, and vision coverage.
• Retirement benefits.
• Learning and development stipend.
• Generous PTO.
• Commuter stipend.
• Equity-based compensation subject to board approval.