AI Safety Research Engineer & Alignment 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

Job summary

Anthropic is seeking a Research Engineer in Alignment Science to design and run rigorous ML experiments focused on AI safety and alignment. You will balance scientific inquiry with engineering execution, collaborating across Interpretability, Fine-Tuning, and Frontier Red Team.

Based in London with a hybrid policy, you will contribute to exploratory research on risks from advanced AI systems and help advance Anthropic's Responsible Scaling Policy through hands-on experimentation.

Qualifications

• Significant software, ML, or research engineering experience.
• Experience contributing to empirical AI research projects.
• Familiarity with technical AI safety research.

Responsibilities

• Perform exploratory experimental research on AI safety in alignment with team goals.
• Collaborate with Interpretability, Fine-Tuning, and Frontier Red Team.
• Develop experiments to understand risks from powerful AI systems.
• Contribute ideas, figures, and writing to research papers, blogs, and talks.

Skills

Software engineering

ML research

Experiment design

Education

PhD or MSc in CS/ML

Tools

Kubernetes

Python

PyTorch/TensorFlow

Job description

Anthropic is seeking a Research Engineer in Alignment Science to design and run rigorous ML experiments focused on AI safety and alignment. You will balance scientific inquiry with engineering execution, collaborating across Interpretability, Fine-Tuning, and Frontier Red Team.

Based in London with a hybrid policy, you will contribute to exploratory research on risks from advanced AI systems and help advance Anthropic's Responsible Scaling Policy through hands-on experimentation.