Research Engineer / Scientist, Alignment Science

Anthropic is seeking a Research Engineer / Scientist for their Alignment Science team. This role involves building and running elegant and thorough machine learning experiments to help understand and steer the behavior of powerful AI systems. The focus is on making AI helpful, honest, and harmless, with an emphasis on risks from powerful future systems.

Key responsibilities include:

• Contributing to exploratory experimental research on AI safety
• Testing the robustness of safety techniques
• Running multi-agent reinforcement learning experiments
• Building tooling to evaluate LLM-generated jailbreaks
• Writing scripts and prompts for evaluation questions
• Contributing to research papers, blog posts, and talks
• Running experiments that feed into key AI safety efforts

The ideal candidate should have:

• Significant software, ML, or research engineering experience
• Experience contributing to empirical AI research projects
• Familiarity with technical AI safety research
• Preference for fast-moving collaborative projects
• Willingness to pick up slack outside of job description
• Care about the impacts of AI

Strong candidates may also have:

• Experience authoring research papers in ML, NLP, or AI safety
• Experience with LLMs and reinforcement learning
• Experience with Kubernetes clusters and complex shared codebases

This role offers a competitive salary range of $280,000 - $625,000 USD, along with equity and comprehensive benefits. The position is hybrid, with an expectation to be in the office at least 25% of the time, and a preference for candidates able to be based in the Bay Area.

Anthropic values diversity and is committed to creating an inclusive environment. They encourage applications from candidates who may not meet every qualification but are passionate about AI safety and align with their mission.