[Expression of Interest] Research Engineer / Scientist, Alignment - London

The role

You will build and run machine learning experiments to understand and steer the behavior of powerful AI systems. The role involves exploratory research on AI safety, focusing on risks from powerful future systems.

What you will do

• Test the robustness of safety techniques by training language models to subvert them
• Run multi-agent reinforcement learning experiments to test techniques like AI Debate
• Build tooling to evaluate the effectiveness of novel LLM-generated jailbreaks
• Write scripts and prompts to produce evaluation questions for model reasoning
• Contribute ideas, figures, and writing to research papers, blog posts, and talks
• Run experiments that feed into key AI safety efforts like the Responsible Scaling Policy

Required qualifications

• Significant software, ML, or research engineering experience
• Some experience contributing to empirical AI research projects
• Some familiarity with technical AI safety research
• Prefer fast-moving collaborative projects to extensive solo efforts
• Pick up slack, even if it goes outside your job description
• Care about the impacts of AI
• Bachelor’s degree or an equivalent combination of education, training, and/or experience
• A field relevant to the role as demonstrated through coursework, training, or professional experience

Nice to have

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

Benefits

• Competitive compensation and benefits
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Office space

Before you apply

• All interviews are conducted in Python
• You must be based at least 25% in London
• Visa sponsorship is available but not guaranteed for every role or candidate

About the company

Anthropic is a public benefit corporation headquartered in San Francisco. Its mission is to create reliable, interpretable, and steerable AI systems.