Research Scientist, Frontier Red Team (Autonomy)

Details

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.

We are looking for Research Scientists to develop and productionize advanced autonomy evaluations on our Frontier Red Team. Our goal is to develop and implement a gold standard of advanced autonomy evals to determine the AI Safety Level (ASL) of our models. This will have major implications for the way we train, deploy, and secure our models, as detailed in our Responsible Scaling Policy (RSP).

We believe that developing autonomy evals is one of the best ways to study increasingly capable and agentic models. If you’ve thought particularly hard about how models might be agentic and associated risks, and you’ve built an eval or experiment around it, we’d like to meet you.

Please note:

• We will be prioritizing candidates who can start ASAP and can be based in either our San Francisco or London office.
• We’re still iterating on the structure of our team. It is possible that this role might end up being the people manager of a few other individual contributors (ICs). If you would be interested in people management, you may express interest in the application.

Responsibilities

• Lead the end-to-end development of autonomy evals and research, including risk and capability modeling, designing, implementing, and running these evals regularly.
• Quickly iterate on experiments to evaluate autonomous capabilities and forecast future capabilities.
• Provide technical leadership to Research Engineers to scope and build scalable and secure infrastructure for running large-scale experiments.
• Communicate evaluation outcomes to Anthropic teams, policy stakeholders, and research collaborators.
• Collaborate with other teams to improve infrastructure and design safety techniques for autonomous capabilities.

Requirements

• Background in machine learning with experience leading experimental research on LLMs, multimodal models, and/or agents.
• Strong Python-based engineering skills.
• Ability to solve ambiguously scoped problems.
• Experience designing and running experiments, iterating quickly to solve ML problems.
• Thrive in collaborative environments including pair programming.
• Experience training, working with, and prompting models.

Benefits

Anthropic is a public benefit corporation headquartered in San Francisco offering competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a collaborative office environment.

Additional details:

• Education: Bachelor's degree or equivalent experience required.
• Hybrid work policy: Staff expected to be in office at least 25% of the time; some roles may require more.
• Visa sponsorship available, with legal support.
• Inclusive hiring encouraged.
• Focus on impactful AI research through large-scale efforts and collaboration.