← All roles

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

Anthropic· AI Research & Engineering
Apply on company site
Hybrid (London, UK)£260k - £370kfull-timePosted 11mo ago

About the role

Research Engineer role focusing on exploratory experimental research in AI safety and alignment, combining scientific and engineering work to understand and steer behaviors of powerful AI systems, with collaboration across Interpretability, Fine-Tuning, and Frontier Red Team.

Responsibilities

  • Testing the robustness of safety techniques by training language models to subvert our safety techniques, and evaluating effectiveness of interventions.
  • 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 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, including the Responsible Scaling Policy.

Qualifications

  • Have significant software, ML, or research engineering experience
  • Have some experience contributing to empirical AI research projects
  • Have 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

Skills

Required:Software engineering / ML engineering experienceEmpirical AI researchAI safety knowledgePython

Benefits

  • Competitive compensation and benefits
  • optional equity donation matching
  • generous vacation and parental leave
  • flexible working hours
  • lovely office space
Last updated Jul 8, 2026. Interested? Apply on the company site.

About Anthropic

building reliable, interpretable, and steerable AI systems

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

ai-infrastructure-and-developmentliquid-ai-recruiting-targetsetter-30setter-30-2026-q1wing-list-2026wing-list-2026-giga-stage
Company profileWebsite

More open roles at Anthropic