AI Alignment Research Engineer & Scientist

anthropic; Greater London; Hybrid; GBP 260,000 - 370,000; Full time

Benefits offered by this job

Equity donation matching

Generous vacation

Parental leave

Flexible working hours

London office

Job summary

Anthropic is seeking a Research Engineer in Alignment Science to design and run rigorous ML experiments aimed at understanding and steering the behavior of advanced AI systems. You will work across teams to explore safety challenges and contribute to papers, blog posts, and talks.

The role emphasizes collaboration, empirical AI research, and hands-on engineering with a focus on safety, alignment, and responsible scaling. Based in London with travel to San Francisco as needed.

Qualifications

• Bachelor’s degree or equivalent combination of education, training, and experience.
• Experience contributing to empirical AI research projects.
• Familiarity with technical AI safety research.

Responsibilities

• Run exploratory experiments to understand alignment safety in AI systems.
• Build tooling to evaluate safety interventions and model behavior.
• Collaborate with Interpretability, Fine-Tuning, and Frontier Red Team to advance safety goals.

Skills

Software/ML engineering

Empirical AI research

AI safety familiarity

Collaborative teamwork

Python proficiency

Education

Bachelor's degree

Tools

Kubernetes

Git

Job description

Anthropic is seeking a Research Engineer in Alignment Science to design and run rigorous ML experiments aimed at understanding and steering the behavior of advanced AI systems. You will work across teams to explore safety challenges and contribute to papers, blog posts, and talks.

The role emphasizes collaboration, empirical AI research, and hands-on engineering with a focus on safety, alignment, and responsible scaling. Based in London with travel to San Francisco as needed.