Alignment Research Engineer - Safe AI & Experimentation

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

Benefits offered by this job

Equity donation matching

Vacation and parental leave

Flexible working hours

Office space

Job summary

Anthropic Limited in London seeks a Research Engineer on Alignment Science to design and run careful ML experiments that help understand and steer the behavior of powerful AI systems. You’ll blend scientist curiosity with engineering rigor, exploring safety, openness, and harm reduction in collaboration with Interpretability, Fine-Tuning, and Frontier Red Team.

Based in London with occasional travel to San Francisco, you will contribute to projects like testing safety techniques, multi-agent RL

Qualifications

• Significant software, ML, or research engineering experience.
• Experience contributing to empirical AI research projects.
• Familiarity with technical AI safety research.
• Ability to work in fast-moving, collaborative projects.

Responsibilities

• Run exploratory experiments on AI safety in collaboration with cross-functional teams.
• Develop tooling and prompts for evaluating model safety and alignment.
• Contribute ideas and writeups to research papers, blogs, and talks.
• Support the Responsible Scaling Policy through hands-on experimentation.

Skills

Software engineering

ML research

AI safety familiarity

Python

Team collaboration

Education

Bachelor’s degree or equivalent

Tools

Kubernetes

Job description

Anthropic Limited in London seeks a Research Engineer on Alignment Science to design and run careful ML experiments that help understand and steer the behavior of powerful AI systems. You’ll blend scientist curiosity with engineering rigor, exploring safety, openness, and harm reduction in collaboration with Interpretability, Fine-Tuning, and Frontier Red Team.

Based in London with occasional travel to San Francisco, you will contribute to projects like testing safety techniques, multi-agent RL