The role is a Research Engineer / Scientist focused on Alignment science within the AI Research & Engineering department at Anthropic. Based in London, the position requires a hybrid working arrangement with travel to San Francisco. The role involves designing and running sophisticated machine learning experiments to evaluate and improve safety techniques for advanced AI systems. Candidates should have strong software, machine learning, and research engineering experience, familiarity with AI safety research, and the ability to collaborate in fast‑moving, interdisciplinary teams. Successful applicants will contribute to experimental projects, tooling, evaluation scripts, and research publications while supporting Anthropic’s mission of building reliable and steerable AI.
[Expression of Interest] Research Engineer / Scientist, Alignment - London at Anthropic
Hybrid - London, UK
More jobs at AnthropicSalary
GBP 260,000 - 370,000
Requirements
Skills
- 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
- Ability to pick up slack even if it goes outside job description
- Care about impacts of AI
- 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
- Bachelor’s degree or an equivalent combination of education, training, and/or experience
Responsibilities
- Test robustness of safety techniques by training language models to subvert safety techniques
- Run multi‑agent reinforcement learning experiments to test techniques like AI Debate
- Build tooling to efficiently evaluate the effectiveness of novel LLM‑generated jailbreaks
- Write scripts and prompts to efficiently produce evaluation questions to test models’ reasoning abilities in safety‑relevant contexts
- Contribute ideas, figures, and writing to research papers, blog posts, and talks
- Run experiments that feed into key AI safety efforts at Anthropic, such as the design and implementation of the Responsible Scaling Policy
Technologies
PythonLLMKubernetesReinforcement learningMulti‑agent reinforcement learning
See if your resume is ready for this job
See how our AI can optimize your resume and improve your chances for this role.