Research Engineer / Scientist, Alignment at Anthropic

On-site - San Francisco, CA

Apply
More jobs at Anthropic

Anthropic is seeking a Research Engineer / Scientist for its Alignment Science team in San Francisco. The role involves designing, running, and analyzing machine learning experiments to improve the safety and reliability of advanced AI systems. Candidates will collaborate across multiple research groups, contribute to safety policy development, and publish research findings. The position offers competitive pay, benefits, equity options, and a flexible work environment in a collaborative setting.

Requirements

Skills

  • 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

Responsibilities

  • Build and run machine learning experiments to understand and steer AI behavior
  • Conduct exploratory research on AI safety focusing on risks from powerful future systems
  • Collaborate with Interpretability, Fine‑Tuning, and Frontier Red Team teams
  • Run multi‑agent reinforcement learning experiments to test safety techniques
  • Build tooling to evaluate the effectiveness of novel LLM‑generated jailbreaks
  • Write scripts and prompts to generate evaluation questions for safety‑relevant contexts
  • Contribute ideas, figures, and writing to research papers, blog posts, and talks

Technologies

PythonMachine LearningLLMReinforcement 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.