AI Safety Researcher — Investigate Model Behavior & Impact
Typesafe AI, Inc.
TypeSafe in San Francisco seeks a safety researcher to build evals, investigate concerning model behavior, and contribute to rigorous safety discussions. You will document observations from project start to formal records and draft internal communications. You will work with highly talented researchers focused on AI safety, alignment, and interpretability, collaborating across teams to strengthen safety review processes. #J-18808-Ljbffr Typesafe AI, Inc.
Vacancy posted 5 days ago
Similar jobs that could be interesting for youBased on the AI Safety Researcher — Investigate Model Behavior & Impact in San Francisco, CA vacancy
- ...Senior Responsible AI Researcher to lead state-of-the... ...intersection of frontier models, Trust & Safety (T&S), model... ...teaming strategies, and behavioral suites to stress-test... ..., and AI Agents. Investigate emerging safety risks... ...architectures. Lead high-impact collaborative...Suggested
$220k - $300k
...OpenAI Foundation AI is already... ...mission. Advanced AI models will also present... ...jobs and economic impact, AI resilience, and... ...biosecurity, model safety, cybersecurity, children... ...red-teaming them, researching how to interpret,... ...end to end (investigating opportunities across...SuggestedOpenAI Foundation
San Francisco, CA2 days ago$250k
...is a fast-moving nonprofit research lab building the public tech stack for AI evaluation and oversight. We... ...AI chatbots and companions impact mental health and child safety, and we’re improving outcomes... ...measure important emerging AI behaviors that may impact vulnerable...SuggestedVisa sponsorship$250k
...a fast-moving nonprofit research lab building the public tech stack for AI evaluation and oversight... ...of AI agents and their behaviors, and are using these to... ...scientifically valid, and concretely impactful. You will conduct novel... ...or decreasing as models become more capable....SuggestedVisa sponsorship- ...Reflection is a research lab making intelligence... ...on. We build open models that let anyone... ...shape the future of AI. Our mission: make... ...model evals and safety from the ground up... ...topics like model behavior, evaluation design... ...you to do the most impactful work of your...SuggestedWork at officeVisa sponsorship
Sierra Ventures
San Francisco, CA5 days ago $150k - $250k
About Distyl AI Distyl is an applied AI technology... ...organizations.We research and deploy... ...Researchers in AI Systems investigate the governing... ...flow, and emergent behavior across multiple agents and models. Their work identifies... ...of high-impact projects across top...Work at office3 days per weekDistyl AI
San Francisco, CA6 days ago$266k - $335k
...Model Policy Manager, Multimodal Safety | OpenAI Careers Model Policy Manager... ...and have a positive impact on society. Our work spans diverse research and engineering... ...deployments, distribute AI’s benefits widely,... ...that define safe model behavior. Our relevant...Work at officeLocal areaRelocation packageFlexible hoursShift workOpenAI
San Francisco, CA2 days ago$45 - $70 per hour
...Science Help a leading AI lab ensure its models respond to people... ...AI lab is seeking behavioral health experts to... ...and help the lab's researchers define what good looks... ...a background in AI safety, applied ethics, trust... ...teams to work on high-impact initiatives....Contract workPart timeWeekday workMercor
San Francisco, CA22 days ago$380k
About the TeamThe Safety Systems team is responsible... ...to ensure our best models can be safely... ...our commitment to AI safety and fostering... ...robust, safe behavior in AI models, and to... ...breadth of new ML research to address the growing... ...making a significant impact on our mission to build...Work at officeLocal areaFlexible hoursOpenAI
San Francisco, CA6 days ago- ...About the team Models are becoming increasingly... ...of frontier AI systems. # Mitigation... .... Model behavior science : Design experiments... ..., or their safety-relevant capabilities... ...hypothesis-driven research and turning our insights... ...systems which impact production models,...
OpenAI
San Francisco, CA2 days ago $245k - $310k
...Product Manager, Model Behavior San Francisco, CA. About... ...as our work directly impacts many teams. About... ...the future of how our AI models behave in real‑... ...balancing user needs, safety considerations, and technical... ...Partner closely with research, engineering, product...Work at officeRelocation packagekozmetickesluzby.vecnakraska.sk - Jobboard
San Francisco, CA2 days ago- ...OpenAI Foundation seeks a founding grantmaker for its AI Model Safety program. You will turn frontier model safety expertise into a grant... ...end to end, identify opportunities, and collaborate with researchers, institutions, and funders to accelerate safe AI development...
$266k - $335k
Model Policy Manager, National Security Model... ...About the Team Safety Systems manages the... ...and have a positive impact on society. Our work spans diverse research and engineering initiatives... ..., distribute AI’s benefits widely,... ...define safe model behavior. Some of our publications...Work at officeLocal areaWork from homeRelocation packageFlexible hours- Retool is seeking an AI Engineer to own model-driven behavior in production across product surfaces, shaping prompts, retrieval, routing, and tool usage to manage non-determinism. You will build evaluation systems and guardrails to ensure reliable, trustworthy AI features...
$136.44k - $265.11k
...rebuilding biotech for the AI era.When a breakthrough... ...and run AI agents and models directly in their... ...about and use AI to drive impact in your role. Feel free... ...distinguish strong model behavior.QUALIFICATIONS2+ years... ..., and external research partners.Desire to work...Work at officeLocal areaMonday to FridayShift workBenchling
San Francisco, CA2 days ago$164.7k - $339.08k
...Possible.At Pinterest, AI isn't just a... ...and amplifies our impact, and we’re looking... ...organization - Trust and Safety + Content Quality,... ...in quantitative modeling, experimentation... ..., Design, Research, Product Analytics... ...appreciation for the behaviors of our PinnersBuild...Work at officeLocal areaRelocationRelocation packagePinterest
San Francisco, CA4 days ago- ...frontier reasoning models is monitorable... ...practical additional safety mechanism, and today... ...and frontier-risk research. We care most... ...interest in model behavior, alignment, or interpretability... ...training, or investigative model-behavior... ...capable AI systems more monitorable...Work at officeRelocation package
- OpenAI in San Francisco is seeking exceptional researchers to push the frontier of safety mitigations for deployed models. You will help derisk frontier models by developing... ..., control, and alignment to ensure safe AI systems. The role requires strong technical depth...
- OpenAI is seeking researchers and engineers to advance frontier-model research with a focus on safety and alignment. You will train and evaluate models, identify misalignments, and develop scalable measurement and evaluation pipelines to turn failures into safety signals...Relocation package
- ...strengthens OpenAI's safety decisions through... ...of frontier models and safeguards, develop... ...about advanced AI systems. About the role As a researcher on Frontier Assurance... ...will move between investigating specific safety... ...understand relevant system behavior, configurations,...
$171.12k
...making a global impact each day. As we... ...Intelligence (AI) to help make our... ...emerging Fraud Researcher. About the job... ...trends and behaviors on Twilio Network... ...scientists to create ML models to detect fraud... ...in-depth investigations into high-... ...investigations, trust & safety, or security...Local areaRemote workWorldwide- Anthropic is seeking an AI Safety Researcher to advance our understanding of AI alignment and develop practical techniques for building safe and beneficial AI systems. You will conduct original research on constitutional AI, interpretability, and scalable oversight. The...
- Career Launch is seeking an ML Researcher in the San Francisco area toLead projects, drive research execution, and communicate findings with stakeholders. You will move quickly in ambiguous environments, turning complex data into actionable steps and recommendations. This...
- OpenAI is seeking a safety- and security-minded researcher or engineer in San Francisco to design and test practical mitigations for increasingly capable AI agents. The role focuses on oversight, system-level mitigations, and sandboxed environments to ensure safe and autonomous...
$169k - $250k
...code, or iterating with AI. From idea to product,... ...collaboration, join us! The Figma Research team is hiring a... ...and broader business impact. Partnering with... ...form a hypothesis from behavioral data and partner with data... ...Experience partnering with model or evaluation teams,...Remote jobMinimum wageFull timeTemporary workWork at officeLocal areaFlexible hoursShift work- ...looking for a senior-level UX Researcher to help improve the... ...research priorities. Synthesize investigative work into impactful deliverables, such as... ...small user cohorts. Modern AI-driven methodology: Skillfully... ...research repositories, behavioral analytics suites, experimentation...Fixed term contractWork at officeLocal areaRemote workFlexible hours
- Foundation seeks a founding grantmaker for its AI Model Safety program, combining deep technical fluency in frontier model evaluation and a drive to translate safety research into funded initiatives. The role involves sourcing, evaluating, and distributing resources to...
$150k - $250k
TypeSafe AI is an AI lab building machine-native intelligence infrastructure for... ...code into a new shape of AI: System One Models. Based in San Francisco, TypeSafe AI recently... ...choices, and targeted interventions impact model behavior Turn raw model outputs and data into...Work at office- Google is seeking a UX Program Manager to lead Model UX operational processes and coordinate cross‑functional... ..., handling ambiguity, and scaling programs in an AI‑first portfolio. Experience with UX content strategy and user research is highly valued. #J-18808-Ljbffr Google
- We're partnering with a frontier AI research company on a search for a Member of Technical Staff... ...next-generation open-weight foundation models with a mission to make advanced AI... ...alignment gaps Design and build scalable safety evaluation frameworks and automated testing...
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to AI Safety Researcher — Investigate Model Behavior & Impact. Be the first to apply!
Related searches
- criminal researcher San Francisco, CA
- academic researcher San Francisco, CA
- machine learning researcher San Francisco, CA
- survey researcher San Francisco, CA
- music researcher San Francisco, CA
- design researcher San Francisco, CA
- content researcher San Francisco, CA
- legal researcher San Francisco, CA
- online researcher San Francisco, CA
- field researcher San Francisco, CA