Research Engineer / Scientist, Alignment Science - London

You will build and run machine learning experiments to understand and steer powerful AI systems, focusing on safety and beneficial outcomes.

As a Research Engineer on Alignment Science, you'll contribute to exploratory experimental research on AI safety, particularly risks from future powerful systems.

Responsibilities include:

• Designing and running experiments to test AI safety techniques
• Collaborating with teams like Interpretability, Fine-Tuning, and Frontier Red Team
• Contributing to research papers, blog posts, and talks
• Building tooling to evaluate novel LLM-generated jailbreaks
• Writing scripts and prompts to test models' reasoning abilities

Requirements:

• Significant software, ML, or research engineering experience
• Experience contributing to empirical AI research projects
• Familiarity with technical AI safety research
• Ability to work collaboratively and pick up slack
• Care about AI impacts

Strong candidates may also have:

• Experience authoring research papers in machine learning, NLP, or AI safety
• Experience with LLMs, reinforcement learning, or Kubernetes clusters

The annual compensation range for this role is £260,000-£370,000 GBP.

Anthropic offers competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space.