jobs

[Expression of Interest] Research Engineer / Scientist, Alignment - London

About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers,

Company

Anthropic

Location

London, UK

Status

Open

Posted

2025-03-31T18:08:49+00:00

Anthropic's Alignment Science team in London is hiring research engineers and scientists to design and run machine-learning experiments on AI safety, focused on risks from future, highly capable systems. Work spans AI control, alignment stress-testing, multi-agent reinforcement learning, jailbreak evaluation and evaluation tooling, in collaboration with other teams. Candidates should have substantial software, ML or research engineering experience plus some empirical AI research background. Distinctive: interviews are held in Python, and staff must be based at least 25% in London with occasional San Francisco travel.