Search
Go
This job is no longer accepting applications
This listing was closed on Aug 16, 2026.
Browse Open Jobs[Expression of Interest] Research Engineer / Scientist, Alignment - London
Summary by AIEngineer.careers
[Expression of Interest] Research Engineer / Scientist, Alignment - London is a AI Research Scientist role (full-time). with Anthropic. in GREATER LONDON, GB. Compensation shown: $330K–$470K (est.). Imported listing (source: jobs-radar.com). Apply on the employer's site (jobs-radar.com).
Imported listing (source: jobs-radar.com) · Apply on jobs-radar.com
GREATER LONDON · GB
$330K–$470K (est.)
Full-time
SENIOR
The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.
Imported job description
Sourced from jobs-radar.com
Anthropic is seeking a Research Engineer/Scientist to contribute to alignment science research focused on ensuring AI systems are safe and beneficial. This role involves designing and running machine learning experiments to understand and steer the behavior of powerful AI systems, with a focus on risks from future systems. The position is based in London with occasional travel to San Francisco.
Responsibilities
- Design and run ML experiments on AI safety, including testing robustness of safety techniques, running multi-agent RL experiments, building tooling to evaluate LLM-generated jailbreaks, and contributing to research papers and blog posts.
Requirements
- Significant software, ML, or research engineering experience; experience contributing to empirical AI research; familiarity with technical AI safety research; preference for collaborative projects; ability to pick up slack; care about impacts of AI.
Nice to Have
- Experience authoring research papers in ML, NLP, or AI safety; experience with LLMs; experience with reinforcement learning; experience with Kubernetes clusters and complex shared codebases.
Tech Stack
Anthropic
San Francisco · US · 2300+ employees
Anthropic is a premier AI research and safety company that develops the Claude family of foundation models, focusing on safety, interpretability, and steerability. It operates as a public benefit corporation.
