{"schemaVersion":"jobsearcher.job.v1","id":"3f4d674b8dd3674841cfd102","url":"https://jobsearcher.com/jobs/3f4d674b8dd3674841cfd102","canonicalUrl":"https://jobsearcher.com/jobs/3f4d674b8dd3674841cfd102","title":"Research Scientist","description":"About Goodfire\nGoodfire is a research company using interpretability to understand, learn from, and design AI systems. Our mission is to build the next generation of safe and powerful AI—not by scaling alone, but by understanding the intelligence we're building.\n\nScaling has proven powerful, but today's approach is fundamentally limited: we can't meaningfully understand, debug, or shape what models learn. Every engineering discipline has been gated by fundamental science and AI is at that inflection point now.\n\nWe're advancing the science of how AI systems actually work. Treating models as black boxes is an unnecessary handicap—we have access to the structures inside them, and understanding those structures lets us steer what models learn, make them safer and more useful, and extract the vast knowledge they contain. Our goal is to make AI that can be understood, debugged, and shaped like software.\n\nGoodfire is a public benefit corporation headquartered in San Francisco with a team of the world’s top interpretability researchers and engineers from organizations like OpenAI and DeepMind. We're backed by over $200M from B Capital, Menlo Ventures, Lightspeed, Eric Schmidt, and others.\n\nAbout the role\nWe’re looking for a Research Scientist to join our team and develop new techniques for understanding and steering large AI models. You’ll work closely with a small, mission-driven team of scientists and engineers to conduct novel research, build practical tools, and push the field forward.\n\nWhere you might contribute:\n\nInterpretability mechanisms – Foundational research on how models represent and process information.\n\nMoonshots – High-upside bets on novel techniques that could unlock breakthroughs in model understanding.\n\nApplied research & usability – Translating research into tools for real-world users and enterprise applications.\n\nWe’ll determine your pod placement during the interview process based on your background and interests.\n\nKey responsibilities:\n\nConduct original research in interpretability and related fields.\n\nPrototype techniques to visualize and manipulate internal model structures.\n\nCollaborate with engineering to turn research into production-ready tools.\n\nShare your work through publications, demos, and open-source contributions.\n\nHelp define and evolve our research direction.\n\nWhat you’ll bring\nRequired experience\n\nPhD or equivalent experience in ML, computer science, or a quantitative science.\n\nDeep familiarity with large models and a passion for understanding how they work.\n\nFluency in Python and ML frameworks such as PyTorch .\n\nStrong writing and communication skills for explaining complex ideas.\n\nDrive to move quickly and take ownership.\n\nPreferred qualifications\n\nExperience leading research or contributing to open-source codebases.\n\nFamiliarity with interpretability , alignment , or safe model development .\n\nExperience in startup or fast-paced lab environments.\n\nWhere we work\nWe are hiring for this position in our San Francisco HQ. We are in person 5 days a week, with one company-wide remote week per month.\n\n#J-18808-Ljbffr","company":"Gravity Engineering Services","rawCompany":"gravity engineering services","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-07-16T03:14:55.228Z","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":"541690","title":"Other Scientific and Technical Consulting Services","slug":"other-scientific-and-technical-consulting-services"},{"code":"513210","title":"Software Publishers","slug":"software-publishers"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Research Scientist","description":"About Goodfire\nGoodfire is a research company using interpretability to understand, learn from, and design AI systems. Our mission is to build the next generation of safe and powerful AI—not by scaling alone, but by understanding the intelligence we're building.\n\nScaling has proven powerful, but today's approach is fundamentally limited: we can't meaningfully understand, debug, or shape what models learn. Every engineering discipline has been gated by fundamental science and AI is at that inflection point now.\n\nWe're advancing the science of how AI systems actually work. Treating models as black boxes is an unnecessary handicap—we have access to the structures inside them, and understanding those structures lets us steer what models learn, make them safer and more useful, and extract the vast knowledge they contain. Our goal is to make AI that can be understood, debugged, and shaped like software.\n\nGoodfire is a public benefit corporation headquartered in San Francisco with a team of the world’s top interpretability researchers and engineers from organizations like OpenAI and DeepMind. We're backed by over $200M from B Capital, Menlo Ventures, Lightspeed, Eric Schmidt, and others.\n\nAbout the role\nWe’re looking for a Research Scientist to join our team and develop new techniques for understanding and steering large AI models. You’ll work closely with a small, mission-driven team of scientists and engineers to conduct novel research, build practical tools, and push the field forward.\n\nWhere you might contribute:\n\nInterpretability mechanisms – Foundational research on how models represent and process information.\n\nMoonshots – High-upside bets on novel techniques that could unlock breakthroughs in model understanding.\n\nApplied research & usability – Translating research into tools for real-world users and enterprise applications.\n\nWe’ll determine your pod placement during the interview process based on your background and interests.\n\nKey responsibilities:\n\nConduct original research in interpretability and related fields.\n\nPrototype techniques to visualize and manipulate internal model structures.\n\nCollaborate with engineering to turn research into production-ready tools.\n\nShare your work through publications, demos, and open-source contributions.\n\nHelp define and evolve our research direction.\n\nWhat you’ll bring\nRequired experience\n\nPhD or equivalent experience in ML, computer science, or a quantitative science.\n\nDeep familiarity with large models and a passion for understanding how they work.\n\nFluency in Python and ML frameworks such as PyTorch .\n\nStrong writing and communication skills for explaining complex ideas.\n\nDrive to move quickly and take ownership.\n\nPreferred qualifications\n\nExperience leading research or contributing to open-source codebases.\n\nFamiliarity with interpretability , alignment , or safe model development .\n\nExperience in startup or fast-paced lab environments.\n\nWhere we work\nWe are hiring for this position in our San Francisco HQ. We are in person 5 days a week, with one company-wide remote week per month.\n\n#J-18808-Ljbffr","datePosted":"2026-07-16T03:14:55.228Z","dateModified":"2026-07-16T03:14:55.228Z","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":"3f4d674b8dd3674841cfd102"},"url":"https://jobsearcher.com/jobs/3f4d674b8dd3674841cfd102"}}