Researcher, Recursive Self-Improvement Safety
OpenAI, Inc.
About the team Models are becoming increasingly capable- moving from tools that assist humans to agents that can plan, execute, and adapt in the real world. Mitigating the frontier risks resulting from these capabilities is paramount to OpenAI's ability to continue deploying models safely. The Preparedness team is dedicated to addressing these critical risks. Our work includes: 1. Measurement. Monitoring and predicting the evolving capabilities of frontier AI systems. 2. Mitigation. Keeping misalignment safeguards, alignment tools, and on track to adequately address extreme threats that might arise in the future. 3. Coordination. Setting mitigation targets by maintaining OpenAI's preparedness framework, and partnering with other staff to achieve these targets. This is urgent, fast-paced work that has far-reaching implications for the company and for society. About the role Preparedness is hiring strong technical executors to support preparations for accelerated AI development, which may culminate in recursive self-improvement. This work relies on anticipating misalignment risks that might exist in the future, but might not exist now; so it's especially important that people in this role are tasteful and strategic. The role is wide-ranging, covering any mitigation for loss of control risk, spanning the design and implementation of better pre-deployment risk-assessment, control measures, RSI-relevant training interventions, and turning one's technical work into established institutional practices and external-facing communications. Below is a subset of our focus areas: Scalable oversight: Establishing practices for model misbehavior monitoring and oversight which remain effective in superhuman model capability regimes, with a focus on bridging from today's monitoring approaches to future-proof ones. Automated auditing: As model capabilities increase, we'll increasingly rely on automated approaches for finding the most severe forms of model misalignments. We'll both need to sift through large swaths of production traffic to find the most egregious misalignments, and reliably elicit tail risks before deployment. Rigorous monitorability: Rigorous testing and red-teaming of our measurements of model misbehavior related to loss-of-control (e.g. reward hacking, sandbagging, scheming). This includes better understanding, and e.g. preparing for potential losses of Chain-of-Thought monitorability. Model behavior science : Design experiments and evaluations to understand the extent to which models are problematically misaligned, or their safety-relevant capabilities lag behind dangerous capabilities. This may include training model organisms of misbehavior for behaviors not currently present in production, or training interventions to increase safety-relevant capabilities. Coordination and verification : Prototype technical mechanisms for verifying compliance with potential future AI safety agreements. AI R&D risk measurement: Track progress toward automation of technical staff to inform OpenAI's near-term investments in alignment and security. Maintaining and strengthening RSI safety cases: We're especially interested in identifying and addressing blindspots of mitigation areas which we may have missed. Generally, our team alternates between performing rigorous hypothesis-driven research and turning our insights into interventions or control systems which impact production models, with occasional support of engineering teams. In this role, you will: Carefully consider the problems OpenAI might face in the future and how to prepare for them. Turn an open-ended objective like "prepare for future misalignment threats" into a much more concrete direction (e.g. "stress-test monitors for scheming") - prioritizing the work that is most useful to start right now. Execute quickly, building scrappy prototypes, and then improving them iteratively until they become established components of our safety pipelines. Secure buy-in from other staff at OpenAI when necessary, and communicate your work clearly. Collaborate with or manage other staff as needed, since we might need to rapidly scale to tackle these problems quickly. You might thrive in this role if you: Are an exceptional technical executor. Have strong strategic and research taste: you can prioritize effectively in domains with weak feedback loops. Are passionate about mitigating the risks associated with recursive self-improvement. Are driven by a desire to do whatever work most positively impacts the future of AI development. Bonus: you have already done work in one of the domains listed above (ML research, AI alignment, AI verification etc). About OpenAI OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of the capabilities of AI systems and seek to safely deploy them to the world through our products. AI is an extremely powerful tool that must be created with safety and human needs at its core, and to achieve our mission, we must encompass and value the many different perspectives, voices, and experiences that form the full spectrum of humanity. We are an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic. For additional information, please see OpenAI's Aff... . Background checks for applicants will be administered in accordance with applicable law, and qualified applicants with arrest or conviction records will be considered for employment consistent with those laws, including the San Francisco Fair Chance Ordinance, the Los Angeles County Fair Chance Ordinance for Employers, and the California Fair Chance Act, for US-based candidates. For unincorporated Los Angeles County workers: we reasonably believe that criminal history may have a direct, adverse and negative relationship with the following job duties, potentially resulting in the withdrawal of a conditional offer of employment: protect computer hardware entrusted to you from theft, loss or damage; return all computer hardware in your possession (including the data contained therein) upon termination of employment or end of assignment; and maintain the confidentiality of proprietary, confidential, and non-public information. In addition, job duties require access to secure and protected information technology systems and related data security obligations. No response will be provided to inquiries unrelated to job posting compliance. We are committed to providing reasonable accommodations to applicants with disabilities, and requests can be made via this link. OpenAI Global Applicant Privacy Policy. At OpenAI, we believe artificial intelligence has the potential to help people solve immense global challenges, and we want the upside of AI to be widely shared. Join us in shaping the future of technology. #J-18808-Ljbffr OpenAI, Inc.
- ...and deploy stress tests, automated audits, and mitigation strategies, collaborating across teams to turn insights into repeatable safety processes. The role requires strong technical execution, strategic judgment, and clear communication to leadership. You will help scale...Suggested
$150k - $250k
...goods, and global social organizations.We research and deploy technologies that power AI-... ...Distyl itself. Our work spans research into self-constructing systems, the development of... ...don’t just want to drive incremental improvements on benchmarks or optimize an existing...SuggestedWork at office3 days per week$380k
About the TeamSafety Research at OpenAI is responsible for ensuring our most capable models... ...be safely deployed in the real world. The Safety Training team develops the research and... ...and the core post-training work needed to improve production models.About the RoleWe are seeking...SuggestedWork at officeLocal areaFlexible hours$259.2k - $324k
Scale Labs, Research Scientist — AI Safety and AlignmentAs the leading data and evaluation partner for frontier AI companies, Scale plays... ...understanding failure modes in multi-agent systems and recursive self-improvement. We collaborate closely with partners across industry...SuggestedFull time- Alterra Labs in the United States is seeking an ML Researcher specializing in post-training infrastructure to advance safety and alignment in healthcare and life sciences.... ..., you will help understand model behavior, improve capabilities on long horizon, multi-modal tasks...Suggested
- Job Title: ML Researcher, Post-Training Infrastructure About Alterra Labs: Alterra Labs is a frontier research lab for AI safety and alignment in healthcare and life sciences. We are looking... ...to understand model behavior and improve model capabilities on complex, long...Full time
- ...About the Team OpenAI's Safety Research organization works to ensure that our most capable AI models can be deployed safely and responsibly... ..., and deployment teams to translate findings into improvements across OpenAI's models and products. About the Role We...Full time
$142.08k - $307.9k
...visa sponsorship * The Vulnerability Researcher is responsible for analyzing systems, software... ...in cloud security controls, and improves and maintains cloud testing standards... ...prioritize workload to meet commitments. ~ Self-motivated with a strong sense of urgency...Work experience placementLocal areaRemote work- ...Solving Self-Improving Superintelligence The human brain is a sponge. Today’s AI brains are brittle and rigid. At Letta, we’re building... ...every day. We’re assembling a world-class team of researchers and engineers to solve AI’s hardest problem: making machines...Full time
- ...Proximal is building the research systems needed to identify what models can't yet do, build... ...them, measure whether those capabilities improve, and continuously produce the data that... ...useful conclusions from messy results Self-directed and relentless, you take ownership...
$285k - $380k
...quickly growing group of committed researchers, engineers, policy experts,... ...science at a leading AI safety company. Responsibilities... ...psychometric techniques to analyze and improve interviewer calibration and... ...~ Experience building self-service analytics tools or dashboards...Work at officeLocal areaVisa sponsorshipFlexible hours$275k
...About Plato Plato is an applied research lab building the foundational... ...Work with the frontier: Build safety environments and benchmarks... ...measure how well AI models can improve themselves and other models.... ...Measure AI research automation and self-improvement. Define tasks,...Relocation$256.9k - $333.4k
...autonomous systems.Join Cisco’s AI Threat Intelligence and Security Research team to design the frontline defense for enterprise AgenticOps!... ..., and iterate on sophisticated adversarial red-teaming and safety benchmarking across foundation models, fine-tuned LLMs, and...Full timeTemporary workWork experience placementLocal areaFlexible hours- OpenAI, Inc. seeks exceptional researchers to push the frontier of safety mitigations and to derisk frontier models. You will develop novel safety approaches and apply techniques from interpretability, control, and alignment to ensure deployed models remain safe at scale...
- ### About the Team The [Safety Systems team]( is responsible for various safety work to... ...and transparency. The Model Safety Research team aims to fundamentally advance our capabilities... ...s core model training and launch safety improvements in OpenAI’s products. Set the...Full time
- ...appropriately. The Chat and Multimodal Safety team is responsible for ensuring that... ...across these experiences. We develop the research, training methods, and evaluations needed... ..., and inference tradeoffs. Have improved frontier model behavior through post-training...Full timeWork at officeRelocation package
- ...ABOUT THE COMPANY We're building autonomous research agents for recursive self-improvement (multi-agent systems that propose, run, and analyze machine learning experiments). We're a small, well-funded team that works onsite in San Francisco. ABOUT THE ROLE...Full time
- ...ABOUT THE COMPANY We're building autonomous research agents for recursive self-improvement (multi-agent systems that propose, run, and analyze machine learning experiments). We're a small, well-funded team that works onsite in San Francisco. ABOUT THE ROLE...Full timeShift work
- ...monitorability, and speculative methods to improve monitorability. While we mostly focus on... ...monitoring can be a practical additional safety mechanism, and today our monitoring... ...evaluations, monitoring, and frontier-risk research.We care most about monitorability where the...Full timeWork at officeRelocation package
$100 per hour
...creative and technical talent with leading AI research labs. Headquartered in San Francisco,... ...feedback to AI research teams to improve training data quality and downstream... ...Meta-Learning . Experience with Recursive Self-Improvement . Interest in AI for Science...Remote jobContract workSummer work- ...ABOUT THE COMPANY We're building autonomous research agents for recursive self-improvement (multi-agent systems that propose, run, and analyze machine learning experiments). We're a small, well-funded team that works onsite in San Francisco. ABOUT THE ROLE...Full timeShift work
- TypeSafe AI is seeking a safety researcher to examine model behavior and help evaluate safety concerns within the team. You’ll build evals, document findings, and contribute to responsible research practices. During the six-week period, you’ll set up access, meet the team...
- ...About the Team The Agent Safety team works to ensure that increasingly capable AI agents... ...re looking for a safety&security minded researcher or engineer who can reason rigorously... ...tool use, and other harmful outcomes. Improve the safety–productivity tradeoff by measuring...Full timeWork at officeRelocation package
- ...ABOUT THE COMPANY We're building autonomous research agents for recursive self-improvement (multi-agent systems that propose, run, and analyze machine learning experiments). We're a small, well-funded team that works onsite in San Francisco. ABOUT THE ROLE...Full timeShift work
- ...Overview Pharos is an early-stage startup dedicated to improving patient safety in hospitals through advanced AI-powered reporting and analytics... ...a pivotal role as a founding member of the clinical AI research team at Pharos. As a Physician AI Researcher, you will...Full timeWork at office
- ...hardware). - Train and tune policies, curate data, and iterate to improve real-world performance. - Write production-quality code that... ...cases and observe robots in deployment contexts. - Bridge research and operations: translate research advances into deployable...
- ...models and agents for cyber defense. We’re looking for a security researcher to explore what these systems can do on difficult, real-world... ...realistic tasks, and work with our model researchers to improve their capabilities. As an early member of the team, you’ll...
$247k - $396k
...'s mission is to deliver the benefits of self-driving technology safely, quickly, and broadly... ...Computer Science, or Robotics (Top-tier research lab background) Deep expertise in... ...of everything we do is our commitment to safety. Building best-in-class self-driving technology...Work at officeLocal area3 days per week$150k
...apps out of POCs and into production. We eliminate the risk and improve the reliability of LLM apps by haizing them – i.e. rigorously,... ...proactively, and continuously fuzz-testing them. We are looking for Research Engineers to help develop our reliability platform, with a...Visa sponsorship$140k - $242k
...Lead Security Researcher Pi.Security · San Francisco, CA · Full-time · Onsite, 5 days a week About Pi.Security Pi is building... ...is part of how software gets designed, reviewed, shipped, and improved. Pi was recognized on Fast Company's 2026 Next Big Things...Permanent employmentFull timeWork at officeFlexible hours
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to Researcher, Recursive Self-Improvement Safety. Be the first to apply!
- independent researcher San Francisco, CA
- content researcher San Francisco, CA
- data collection researcher San Francisco, CA
- human factors researcher San Francisco, CA
- qualitative researcher San Francisco, CA
- researcher San Francisco, CA
- product researcher San Francisco, CA
- legal researcher San Francisco, CA
- senior researcher San Francisco, CA
- machine learning researcher San Francisco, CA





