Research Engineer, Interpretability
San Francisco
Workplace: OnsiteFull timeUSD 315,000 - 560,000 annuallyFunction: Research & Scientific (R&D)Education: bachelorsSkills: ["Collaboration","Communication","Prioritization","Problem-solving"]Join the Interpretability team to design and analyze experiments on mechanistic interpretability of large language models, build scalable research workflows and tooling, and help other teams apply interpretability techniques to improve model safety. You’ll work with researchers and engineers on large-scale AI systems, contributing to cutting-edge projects and reporoducing results across production models.
Loading
Loading job details...
Preparing the role view and application actions.

