← All roles

Research Engineer / Scientist, Alignment

Anthropic· AI Research & Engineering
Apply on company site
Hybrid (San Francisco, CA)$350k - $500kFull-timePosted 11mo ago

About the role

Research Engineer on Alignment Science focusing on exploratory experimental research in AI safety, collaborating with Interpretability, Fine-Tuning, and Frontier Red Team to study risks from powerful future systems and advance scalable oversight, AI control, automated alignment research, and model welfare.

Responsibilities

  • Testing the robustness of safety techniques by training language models to subvert safety techniques and evaluating effectiveness of interventions
  • Running multi-agent reinforcement learning experiments to test techniques like AI Debate
  • Building tooling to efficiently evaluate the effectiveness of novel LLM-generated jailbreaks
  • Writing scripts and prompts to efficiently produce evaluation questions to test models’ reasoning abilities in safety-relevant contexts
  • Contributing ideas, figures, and writing to research papers, blog posts, and talks
  • Running experiments that feed into key AI safety efforts at Anthropic, including design and implementation of the Responsible Scaling Policy

Qualifications

  • 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 over extensive solo efforts
  • Ability to pick up slack and work beyond defined job description
  • Concern for the impacts of AI

Skills

Required:Software development / ML engineeringempirical AI research
Nice to have:AI safety / alignment knowledge

Benefits

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