jobs
Research Engineer / Scientist, Alignment
Anthropic’s Alignment Science team conducts experimental research into the safety and behavior of powerful AI systems. This role is suited to someone who combines scientific curiosity with…
En inglés
- Company
- Anthropic
- Location
- San Francisco, CA, United States
- Status
- Closed
- Posted
- 2026-11-10 03:34 UTC
Anthropic's Alignment Science team is hiring a research engineer or scientist to run experimental work on the safety and behavior of powerful AI systems. The job involves designing machine-learning experiments across areas such as scalable oversight, AI control, alignment stress-testing, automated alignment research, assessments, safeguards, and model welfare, with possible projects training models to subvert safety techniques, running multi-agent reinforcement-learning experiments, building tools to evaluate LLM-generated jailbreaks, and writing evaluation questions. It also includes contributing to papers and talks. The posting asks for significant software, ML or research-engineering experience and some empirical AI research background; Python interviews, Bay Area candidates preferred, hybrid in San Francisco.
Original job posting