AI Safety Research Engineer — ML, RL & LLMs (London)

Anthropic in London, UK, seeks a full-time Alignment Scientist to develop and execute ML experiments, build evaluation tooling for LLM safety, and explore multi-agent RL like AI Debate. Occasional travel to San Francisco is expected; base location London.

You will contribute to safety research papers, blogs, and internal docs, working with a collaborative team. A strong background in software engineering or ML, plus proficiency in Python, is required.

#J-18808-Ljbffr…