Research Engineer / Scientist, Alignment Science

Safetytalent; San Francisco (CA); On-site; USD 100,000 - 150,000; Full time

Job summary

Safetytalent is seeking a Research Engineer / Scientist focused on Alignment Science in San Francisco, California. The role involves building and running machine learning experiments, contributing to research on AI safety, and collaborating on safety techniques.

The ideal candidate will work on designing evaluations to test models and contribute to AI safety efforts, including publications. This position emphasizes collaboration and innovation in understanding AI behavior.

Responsibilities

• Build and run machine learning experiments to understand AI behavior.
• Contribute to exploratory research on AI safety.
• Collaborate on safety techniques testing projects.
• Design evaluations to test models' reasoning abilities.
• Contribute to research papers and blog posts.

Job description

Research Engineer / Scientist, Alignment Science

Anthropic

Responsibilities

• Build and run machine learning experiments to understand and steer the behavior of powerful AI systems, focusing on making AI helpful, honest, and harmless.
• Contribute to exploratory research on AI safety, particularly addressing risks from powerful future systems.
• Collaborate with teams on projects such as testing safety techniques.
• Design and implement evaluations to test models' reasoning abilities in safety-relevant contexts.
• Contribute to research papers, blog posts, and experiments that feed into Anthropic's AI safety efforts.