Research Scientist, AI Interpretability & Safe Models
Gravity Engineering Services Pvt Ltd.
Gravity Engineering Services Pvt Ltd. is seeking a Research Scientist to join our San Francisco HQ. The ideal candidate will develop techniques for understanding large AI models, conduct original research, and translate findings into practical tools. Required qualifications include a PhD in ML or a related field, proficiency in Python and ML frameworks like PyTorch, and strong communication skills. Enjoy a dynamic workplace with a commitment to advancing AI. #J-18808-Ljbffr Gravity Engineering Services Pvt Ltd.
Vacancy posted 4 days ago
Similar jobs that could be interesting for youBased on the Research Scientist, AI Interpretability & Safe Models in San Francisco, CA vacancy
- ...Engineering Services Pvt Ltd. is seeking a passionate researcher focused on mechanistic interpretability. The role involves developing significant research on AI representation and infrastructure to ensure safe models. You will work closely with an enthusiastic team,...Suggested
$295k
About the Team The Personality & Model Behavior team, within OpenAI’s... ...Personal AGI team conducts research on how to shape personalities... ...constraints. About OpenAI OpenAI is an AI research and deployment... ...of AI systems and seek to safely deploy them to the world through...SuggestedWork at officeLocal areaRelocation packageFlexible hours$310k
Research Engineer / Research Scientist - Model Behavior job at OpenAI. San Francisco, CA. About the Team Model behavior... ...taste and intuition for classical AI alignment challenges. In this role... ...of AI systems and seek to safely deploy them to the world through our...Suggested- Radical Numerics is seeking a Member of Technical Staff, Mechanistic Interpretability, to study how multimodal genome language models represent and reason about information. This research-oriented role emphasizes model understanding, driving scientific discovery and innovation...Suggested
$160k - $280k
...time. We are a team of musicians and AI experts, including alumni from... ...re looking for early members of our research team. You’ll work closely with the founding... ...and deploy our state of the art ML models trained with an H100/scientist ratio of >100x. Check out our Suno...SuggestedWork at officeFlexible hours- Granica in Mountain View, CA is building Large Tabular Models (LTMs) and seeks researchers to develop diffusion models and generative learning algorithms. You will collaborate with Prof. Andrea Montanari and Granica's research team to translate research into production...
$350k
...mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and... ...growing group of committed researchers, engineers, policy experts, and... ...When you see what modern language models are capable of, do you wonder,...Temporary workWork at officeRemote workVisa sponsorshipFlexible hours- About the Role The Interpretability team at Anthropic is dedicated to reverse... ...-engineering how trained models work, believing that a... ...crucial for making advanced AI systems safe. This role focuses on mechanistic... ...track record of scientific research (in any field) and some...Remote workVisa sponsorship
$350k
...is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our... ...group of committed researchers, engineers, policy experts... ...yourself as both a scientist and an engineer. As a... ...to keep highly capable models helpful and honest, even...Work at officeVisa sponsorshipFlexible hoursAnthropic
San Francisco, CA3 days ago$216k - $270k
Scale Labs, Research Scientist - AI Controls and Monitoring As the leading data... ...and safeguarding AI models and systems. Building on this... ...layered control, including fail‑safes, oversight protocols, and... ...(e.g., scalable oversight, interpretability, debate). Experience with...Full time- A leading AI research company in San Francisco is seeking a Researcher to drive research in generative modeling and embodied AI. The candidate will define research directions, design novel architectures, and mentor research engineers, contributing to impactful publications...Work at office
- Harrison Clarke is seeking a Research Scientist to join a cutting-edge AI company in San Francisco. You will contribute to developing innovative AI/ML methodologies... ...or related fields and experience with deep learning models. This is an opportunity to work in a highly technical...
- Ludwig Computing is seeking exceptional ML researchers and engineers to advance AI systems and next-generation compute. This hands-on role focuses on making large AI models smaller, faster, and more efficient, combining theory with practical implementation. You will work...
$320k
...is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our... ...group of committed researchers, engineers, policy experts... ...be the year where models reach expert‑level, even... ...surface. As a Research Scientist on FRT focusing on...Work at officeRelocationVisa sponsorshipFlexible hours$350k
...mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and... ...growing group of committed researchers, engineers, policy experts, and... ...with audio with large language models. We care about making safe, steerable...Full timeWork at officeVisa sponsorshipFlexible hoursShift work$350k
...mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and... ...growing group of committed researchers, engineers, policy experts, and... ...Pytorch, or OS internals Language modeling with transformers...Work at officeVisa sponsorshipFlexible hours- ...is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our... ...group of committed researchers, engineers, policy experts... ...Engineer/Research Scientist to join our Pre‑training... ...generation of large language models. In this role, you...Visa sponsorship
$380k
...Future of Computing Research team is an applied... ...new methods, models, and evaluation frameworks... ...of multimodal AI, helping turn... ...Research Engineer / Scientist to join the Future... ...personalization remain aligned, interpretable, and bounded by... ...and seek to safely deploy them to the...Work at officeImmediate startRelocation package- ...a Google Deepmind veteran behind Project Astra, and top-tier AI researchers. As an early member of this team, you will have significant... ...to collaborate with one of the best image and video generation model teams in the world on data collection. Unparalleled Resources...Work at officeVisa sponsorship
Spellbrush
San Francisco, CA3 days ago - Member of Technical Staff - Research Scientist Patronus AI is a frontier lab... ...customers include foundation model labs and Fortune 500 enterprises... ...our path towards safe, human-aligned general intelligence... ...design, analysis, and interpretation of results. Experience writing...
$150k - $300k
About Patronus AI Patronus AI is a frontier... ...simulation research and infrastructure... ...include foundation model labs and Fortune 5... ...Responsibilities As a Research Scientist at Patronus AI,... ...our path towards safe, human‑aligned... ..., analysis, and interpretation of results....Work at office- About the Team The Interpretability team studies internal representations... ...of deep learning models. We are interested in... ...safety of powerful AI systems. Our working... ...OpenAI is seeking a researcher passionate about understanding... ...future models remain safe even as they grow in...
- ...institution based in San Francisco is looking for an Applied Researcher to work on AI-powered products. This role involves delivering innovative... ...Responsibilities include partnering with teams to build AI models and conducting impactful research. #J-18808-Ljbffr Capital...
- OpenAI in San Francisco is searching for a Researcher in Recursive Self-Improvement Safety. This role involves tracking AI threats, developing mitigation strategies, and enhancing model oversight practices. The ideal candidate will transform vague safety objectives into...
- ...financial services firm in San Francisco is seeking an Applied Researcher II to develop innovative AI systems. In this role, you will collaborate with a cross-functional team to build AI foundation models, engage in impactful research, and translate complex work into business...
- Thinking Machines Lab in San Francisco, California, seeks a post-training researcher to bridge model intelligence and practical AI applications. The successful candidate will combine theoretical research with hands-on engineering, writing high-performance code. This exciting...
- ...photorealistic virtual try‑on. You will work on multimodal learning, integrating vision, language, and video modalities into scalable models. A Ph.D. or Master’s in a relevant field is expected, along with proven experience in deep learning frameworks like PyTorch or...
- ...Machines Lab in San Francisco is actively researching audio capabilities, blending rigorous... ...practical engineering to build multimodal AI systems. You will work across pre-training, post-training, and product to develop models that understand and generate audio with high...
- A cutting-edge AI startup is searching for an experienced AI Researcher eager to advance generative AI. This role requires a PhD and 5+ years of research experience, focusing on developing innovative models that harness earth observation. The ideal candidate will demonstrate...Remote job
- ...Sciences in San Francisco is seeking an ML Scientist I/II to join their Foundation Models team, contributing to generative model research in life sciences. The ideal candidate will... ...collaboration with experimental scientists to apply AI solutions to biology and enhance model...Full timeFlexible hours
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Research Scientist, AI Interpretability & Safe Models. Be the first to apply!
Related searches
- research associate scientist San Francisco, CA
- scientist antibody discovery San Francisco, CA
- protein scientist San Francisco, CA
- lead scientist San Francisco, CA
- applied sports scientist San Francisco, CA
- deep learning scientist San Francisco, CA
- lab scientist San Francisco, CA
- principal scientist San Francisco, CA
- molecular biology scientist San Francisco, CA
- senior analytical scientist San Francisco, CA