{"schemaVersion":"jobsearcher.job.v1","id":"0a95068ba519ce74f4368c19","url":"https://jobsearcher.com/jobs/0a95068ba519ce74f4368c19","canonicalUrl":"https://jobsearcher.com/jobs/0a95068ba519ce74f4368c19","title":"Research Engineer - Scalable Interpretability","description":"Research Engineer - Scalable InterpretabilityTransluce is a non-profit research lab building tools for scalable, end-to-end oversight of AI systems. We build world-class, AI-backed analysis tools and use these to set industry standards for evaluation. Our tools are integrated with core agent benchmarks like SWE-bench, while our evaluations are directly underpinning regulation, including our role as EU AI Office's main evaluation developer for harmful manipulation risks.\r\nWe are looking for strong scientists and engineers to help advance our vision of scalable end-to-end oversight assistants, building on our recent advances such as predictive concept decoders and user model extractors. As part of our highly collaborative team, you will learn and grow quickly, creating technology at the frontier of AI research and with high direct impact.\r\nHelp us develop and train scalable interpretability assistants that can predict and detect unexpected and subtle behaviors from models' activations. This includes:\r\nCreating diverse evaluations that range in difficulty. This involves finding naturally occurring interesting and undesirable behaviors exhibited by open-source models.\r\nDeveloping novel architectures and objectives for training interpretability assistants.\r\nScaling up the training and inference pipelines to support up to 1T-scale models.\r\nQualities of a strong candidate:\r\nExperience with fine-tuning language models, designing new architectures, and creating evaluations.\r\nReliable results: good experimental design, epistemic self-awareness and transparency\r\nGenerativeness: coming up with original, productive ideas for unblocking progress\r\nCuriosity: a desire to understand ML systems and how they work\r\nStrong programming ability, including navigating trade-offs between prototyping speed and maintainability\r\nStrong communication skills, low ego, openness to giving and receiving feedback","company":"Transluce","rawCompany":"transluce","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-07-02T01:15:25.600Z","occupations":[{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"27-3091.00","title":"Interpreters and Translators","slug":"interpreters-and-translators"}],"industries":[{"code":"541990","title":"All Other Professional, Scientific, and Technical Services","slug":"all-other-professional-scientific-and-technical-services"},{"code":"541930","title":"Translation and Interpretation Services","slug":"translation-and-interpretation-services"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Research Engineer - Scalable Interpretability","description":"Research Engineer - Scalable InterpretabilityTransluce is a non-profit research lab building tools for scalable, end-to-end oversight of AI systems. We build world-class, AI-backed analysis tools and use these to set industry standards for evaluation. Our tools are integrated with core agent benchmarks like SWE-bench, while our evaluations are directly underpinning regulation, including our role as EU AI Office's main evaluation developer for harmful manipulation risks.\r\nWe are looking for strong scientists and engineers to help advance our vision of scalable end-to-end oversight assistants, building on our recent advances such as predictive concept decoders and user model extractors. As part of our highly collaborative team, you will learn and grow quickly, creating technology at the frontier of AI research and with high direct impact.\r\nHelp us develop and train scalable interpretability assistants that can predict and detect unexpected and subtle behaviors from models' activations. This includes:\r\nCreating diverse evaluations that range in difficulty. This involves finding naturally occurring interesting and undesirable behaviors exhibited by open-source models.\r\nDeveloping novel architectures and objectives for training interpretability assistants.\r\nScaling up the training and inference pipelines to support up to 1T-scale models.\r\nQualities of a strong candidate:\r\nExperience with fine-tuning language models, designing new architectures, and creating evaluations.\r\nReliable results: good experimental design, epistemic self-awareness and transparency\r\nGenerativeness: coming up with original, productive ideas for unblocking progress\r\nCuriosity: a desire to understand ML systems and how they work\r\nStrong programming ability, including navigating trade-offs between prototyping speed and maintainability\r\nStrong communication skills, low ego, openness to giving and receiving feedback","datePosted":"2026-07-02T01:15:25.600Z","dateModified":"2026-07-02T01:15:25.600Z","hiringOrganization":{"@type":"Organization","name":"Transluce","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"0a95068ba519ce74f4368c19"},"url":"https://jobsearcher.com/jobs/0a95068ba519ce74f4368c19"}}