Research Scientist, Safety Post Training

Responsibilities

• Design and run post-training pipelines to study how training choices affect model safety, robustness, and alignment properties.
• Develop interpretability-informed evaluations that reveal how and why models produce unsafe, deceptive, or otherwise undesirable behaviors, and use those insights to guide targeted mitigations.
• Collaborate with policymakers, engineers, and other researchers to translate post-training and interpretability findings into actionable safety standards, evaluation benchmarks, and best practices.

Requirements

• Commitment to promoting safe, secure, and trustworthy AI deployments.
• Experience with post-training and RL techniques such as RLHF, DPO, GRPO, and similar approaches.
• A track record of published research in machine learning, particularly in generative AI.
• At least three years of experience addressing sophisticated ML problems, whether in a research setting or in product development.
• Strong written and verbal communication skills.

Nice to Haves

• Experience with mechanistic interpretability, probing, or other techniques for understanding model internals.
• Familiarity with red-teaming or adversarial evaluation of post-trained models.
• Experience studying failure modes introduced or masked by post-training, such as reward hacking, sycophancy, or alignment faking.

Compensation and Benefits

Compensation packages include base salary, equity, and benefits. Eligible roles receive comprehensive health, dental and vision coverage, retirement benefits, a learning and development stipend, and generous PTO. This role may be eligible for a commuter stipend.