{"schemaVersion":"jobsearcher.job.v1","id":"f8e7410fa1f0fac1cc89fdb3","url":"https://jobsearcher.com/jobs/f8e7410fa1f0fac1cc89fdb3","canonicalUrl":"https://jobsearcher.com/jobs/f8e7410fa1f0fac1cc89fdb3","title":"Research Scientist, Interpretability","description":"About the Role\nThe Interpretability team at Anthropic is dedicated to reverse-engineering how trained models work, believing that a mechanistic understanding is crucial for making advanced AI systems safe. This role focuses on mechanistic interpretability, aiming to discover how neural network parameters map to meaningful algorithms. You will contribute to a solid foundation for understanding neural networks and ensuring their safety, collaborating with teams like Alignment Science and Societal Impacts.\n\nResponsibilities\n\nDevelop methods for understanding Large Language Models (LLMs) by reverse-engineering algorithms learned in their weights.\n\nDesign and run robust experiments, both in toy scenarios and at scale in large models.\n\nCreate and analyze new interpretability features and circuits to better understand model functionality.\n\nBuild infrastructure for running experiments and visualizing results.\n\nWork with colleagues to communicate results internally and publicly.\n\nYou may be a good fit if you:\n\nHave a strong track record of scientific research (in any field) and some prior work on Interpretability.\n\nEnjoy team science and collaborative discovery.\n\nAre comfortable with messy experimental science and inventing new methodologies.\n\nView research and engineering as integrated, writing code, designing experiments, and interpreting results.\n\nCan clearly articulate motivations for your work and effectively communicate learned insights, including null results.\n\nRequired Skills\n\nFamiliarity with Python .\n\nLogistics\n\nMinimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience.\n\nRequired field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience.\n\nLocation-based hybrid policy: Currently, all staff are expected to be in one of our offices at least 25% of the time. This role is based in San Francisco, CA, but remote work may be considered for exceptional candidates on a case-by-case basis.\n\nVisa sponsorship: Visa sponsorship is available.\n\n#J-18808-Ljbffr","company":"Gravity Engineering Services","rawCompany":"gravity engineering services","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-07-16T03:59:47.086Z","occupations":[{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"},{"code":"15-2051.00","title":"Data Scientists","slug":"data-scientists"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"}],"industries":[{"code":"541715","title":"Research and Development in the Physical, Engineering, and Life Sciences (except Nanotechnology and Biotechnology)","slug":"research-and-development-in-the-physical-engineering-and-life-sciences-except-nanotechnology-and-biotechnology"},{"code":"541990","title":"All Other Professional, Scientific, and Technical Services","slug":"all-other-professional-scientific-and-technical-services"},{"code":"541690","title":"Other Scientific and Technical Consulting Services","slug":"other-scientific-and-technical-consulting-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Research Scientist, Interpretability","description":"About the Role\nThe Interpretability team at Anthropic is dedicated to reverse-engineering how trained models work, believing that a mechanistic understanding is crucial for making advanced AI systems safe. This role focuses on mechanistic interpretability, aiming to discover how neural network parameters map to meaningful algorithms. You will contribute to a solid foundation for understanding neural networks and ensuring their safety, collaborating with teams like Alignment Science and Societal Impacts.\n\nResponsibilities\n\nDevelop methods for understanding Large Language Models (LLMs) by reverse-engineering algorithms learned in their weights.\n\nDesign and run robust experiments, both in toy scenarios and at scale in large models.\n\nCreate and analyze new interpretability features and circuits to better understand model functionality.\n\nBuild infrastructure for running experiments and visualizing results.\n\nWork with colleagues to communicate results internally and publicly.\n\nYou may be a good fit if you:\n\nHave a strong track record of scientific research (in any field) and some prior work on Interpretability.\n\nEnjoy team science and collaborative discovery.\n\nAre comfortable with messy experimental science and inventing new methodologies.\n\nView research and engineering as integrated, writing code, designing experiments, and interpreting results.\n\nCan clearly articulate motivations for your work and effectively communicate learned insights, including null results.\n\nRequired Skills\n\nFamiliarity with Python .\n\nLogistics\n\nMinimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience.\n\nRequired field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience.\n\nLocation-based hybrid policy: Currently, all staff are expected to be in one of our offices at least 25% of the time. This role is based in San Francisco, CA, but remote work may be considered for exceptional candidates on a case-by-case basis.\n\nVisa sponsorship: Visa sponsorship is available.\n\n#J-18808-Ljbffr","datePosted":"2026-07-16T03:59:47.086Z","dateModified":"2026-07-16T03:59:47.086Z","hiringOrganization":{"@type":"Organization","name":"Gravity Engineering Services","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"f8e7410fa1f0fac1cc89fdb3"},"url":"https://jobsearcher.com/jobs/f8e7410fa1f0fac1cc89fdb3"}}