Research Engineer / Scientist, Alignment

Anthropic is a public benefit corporation headquartered in San Francisco, focused on creating reliable, interpretable, and steerable AI systems. As a Research Engineer on Alignment Science, you will contribute to exploratory experimental research on AI safety, focusing on risks from powerful future systems (ASL-3 or ASL-4 under the Responsible Scaling Policy), often collaborating with teams including Interpretability, Fine-Tuning, and the Frontier Red Team.

• Build and run elegant and thorough machine learning experiments to understand and steer the behavior of powerful AI systems.
• Contribute to research areas including Scalable Oversight, AI Control, Alignment Stress-testing, Automated Alignment Research, Alignment Assessments, Safeguards Research, and Model Welfare.
• Test 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 novel LLM-generated jailbreaks.
• Write scripts and prompts to produce evaluation questions for safety-relevant reasoning.
• Contribute ideas, figures, and writing to research papers, blog posts, and talks.

• Significant software, ML, or research engineering experience.
• Some experience contributing to empirical AI research projects.
• Familiarity with technical AI safety research.
• Preference for fast-moving collaborative projects.
• Strong candidates may have experience authoring research papers in ML, NLP, or AI safety; experience with LLMs, reinforcement learning, Kubernetes clusters, and complex shared codebases.

Annual salary: $350,000—$500,000 USD.

Anthropic offers competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space.

Interviews are conducted in Python. Candidates should be based in the Bay Area. Visa sponsorship is available, though not for every role or candidate.