AI Alignment Research Engineer & Scientist – Hybrid

Anthropic Limited; City Of London; Hybrid; GBP 260,000 - 370,000; Full time

Benefits offered by this job

Visa sponsorship

Hybrid work policy

Job summary

Anthropic Limited in London is seeking a Research Engineer on Alignment Science to run thorough ML experiments, understand AI safety, and help steer powerful systems. You will blend science and engineering, contribute to exploratory research, and collaborate with Interpretability, Fine-Tuning, and Frontier Red Team.

You may work in a hybrid setup with 25% office time, travel to San Francisco occasionally, and contribute to papers, blog posts, and talks.

Qualifications

• Significant software, ML, or research engineering experience.
• Experience contributing to empirical AI research projects.
• Familiar with technical AI safety research.
• Prefer fast-moving collaborative projects over solo work.

Responsibilities

• Run exploratory ML experiments to steer AI behavior and safety.
• Train language models to test safety techniques and interventions.
• Develop tooling to evaluate LLM safety and jailbreaks.
• Contribute ideas and writing to research papers, blog posts, and talks.
• Collaborate with Interpretability, Fine-Tuning, and Frontier Red Team.

Skills

Software/ML/Research Eng

Empirical AI research

AI safety research

Team collaboration

Education

Bachelor’s degree or equivalent

Tools

Kubernetes

Job description

Anthropic Limited in London is seeking a Research Engineer on Alignment Science to run thorough ML experiments, understand AI safety, and help steer powerful systems. You will blend science and engineering, contribute to exploratory research, and collaborate with Interpretability, Fine-Tuning, and Frontier Red Team.

You may work in a hybrid setup with 25% office time, travel to San Francisco occasionally, and contribute to papers, blog posts, and talks.