Research Engineer - Alignment Science - Remote

Overview

As a Research Engineer on Alignment Science at Anthropic, you will contribute to exploratory experimental research on AI safety, focusing on risks from powerful future systems.

In Short

• Build and run machine learning experiments.
• Focus on AI safety and alignment evaluations.
• Collaborate with teams on AI control and interpretability.
• Contribute to research papers and blog posts.
• Run multi-agent reinforcement learning experiments.
• Test the robustness of safety techniques.
• Develop tooling for evaluating AI safety techniques.
• Work in a collaborative and fast-paced environment.
• Be based in the Bay Area or London with occasional travel.
• Engage in impactful AI research.

Requirements

• Significant software, ML, or research engineering experience.
• Experience in empirical AI research projects.
• Familiarity with technical AI safety research.
• Ability to work collaboratively.
• Interest in the impacts of AI.

Benefits

• Competitive compensation and benefits.
• Optional equity donation matching.
• Generous vacation and parental leave.
• Flexible working hours.
• Collaborative office space.