--- title: 'Researcher, Recursive Self-Improvement Safety at OpenAI' canonical: 'https://feeny.ai/job/researcher-recursive-self-improvement-safety-openai-san-francisco-kz2ncc4b8h2t' type: 'job' last_seen: '2026-09-10' --- # Researcher, Recursive Self-Improvement Safety at OpenAI - **Company:** [OpenAI](https://feeny.ai/companies/openai) - **Location:** San Francisco, CA - **Compensation:** $380k–$500k - **Employment:** full-time - **Posted:** 2026-08-07 - **Last confirmed live:** 2026-09-10 - **Apply:** https://jobs.ashbyhq.com/openai/5a9e68f6-30b5-40c0-aa8c-c822c59140d0 ## Job description ## 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: - Measurement. Monitoring and predicting the evolving capabilities of frontier AI systems. - Mitigation. Keeping misalignment safeguards, alignment tools, and on track to adequately address extreme threats that might arise in the future. - Coordination. Setting mitigation targets by maintaining OpenAI’s[preparedness framework](https://openai.com/index/updating-our-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](https://openai.com/index/deployment-simulation/), [control measures](https://openai.com/index/how-we-monitor-internal-coding-agents-misalignment/), 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](https://openai.com/index/how-we-monitor-internal-coding-agents-misalignment/) 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](https://arxiv.org/abs/2603.05706)[understanding](https://alignment.openai.com/accidental-cot-grading/)[monitorability](https://arxiv.org/abs/2512.18311), 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 Affirmative Action and Equal Employment Opportunity Policy Statement](https://cdn.openai.com/policies/eeo-policy-statement.pdf). 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. To notify OpenAI that you believe this job posting is non-compliant, please submit a report through [this form](https://form.asana.com/?d=57018692298241&k=5MqR40fZd7jlxVUh5J-UeA). 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](https://form.asana.com/?k=bQ7w9h3iexRlicUdWRiwvg&d=57018692298241). [OpenAI Global Applicant Privacy Policy](https://cdn.openai.com/policies/global-employee-and-contractor-privacy-policy.pdf) 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. ## About OpenAI ## Company Overview - **One-liner**: OpenAI is an AI research and deployment company with a mission to ensure that artificial general intelligence (AGI) benefits all of humanity. - **Entity Type**: Private – structured as a nonprofit parent (OpenAI Foundation) governing a for-profit public benefit corporation (OpenAI Group). The company has confidentially submitted a draft S-1 registration statement to the SEC, signaling a potential future IPO. - **Headquarters**: San Francisco, California, USA - **Founded**: 2015 - **Founders**: Sam Altman, Greg Brockman, Ilya Sutskever, John Schulman, Wojciech Zaremba, and others ## Core Business - **Primary industry**: Artificial intelligence research and deployment - **Target customers**: B2B (enterprises via API and platform), B2C (ChatGPT users), and developers (API, open-source models) - **Mission**: To ensure that artificial general intelligence (AGI) – AI systems that are generally smarter than humans – benefits all of humanity. ## Products & Services - **[ChatGPT](https://openai.com/chatgpt)**: Conversational AI assistant available via web and mobile, used by consumers and integrated into enterprise workflows. - **[GPT-4 API](https://openai.com/product)**: Large language model accessed via API for developers to build AI-powered applications (text generation, summarization, code assistance, etc.). - **[DALL-E](https://openai.com/dall-e-3)**: Image generation model that creates images from natural language descriptions. - **[Whisper](https://openai.com/research/whisper)**: Open-source speech recognition system. - **[OpenAI Agents](https://openai.com/)**: Emerging product category focused on autonomous AI agents that can perform tasks on behalf of users (announced June 2026). ## Market Standing - **Valuation**: Not publicly disclosed in the provided sources. Widely reported in the press at ~$300 billion as of early 2026 (post-funding round), but this figure is not confirmed by OpenAI’s official materials. - **Key Metric**: Total funding exceeds $13 billion from Microsoft and other investors. The company has also confidentially filed a draft S-1 with the SEC (see [openai.com](https://openai.com/) – “Confidential submission of draft S-1”). - **Notable Investors/Partners**: Microsoft (strategic partner and largest investor), with additional participation from Thrive Capital, Sequoia Capital, Andreessen Horowitz, and others. - **Growth Signals**: Active hiring with 721 open roles posted; expansion into agent-based products; confidential IPO filing; continued deployment of frontier models. ## Competitive Advantages - **First-mover & brand recognition**: ChatGPT became the fastest-growing consumer app in history, establishing OpenAI as the household name in generative AI. - **Research leadership**: Consistently publishes cutting-edge research (GPT-4, DALL-E 3, Whisper, etc.) and attracts top AI talent. - **Compute & infrastructure**: Exclusive partnership with Microsoft provides massive cloud computing resources (Azure) for training and inference. - **Unique governance structure**: The nonprofit parent ensures mission alignment (AGI benefiting humanity) while the for-profit arm can raise capital and scale products. ## Strategic Focus - **Safe AGI development**: Continued emphasis on safety research, alignment, and responsible deployment (e.g., safety systems, model provenance). - **Enterprise expansion**: Growing ChatGPT Enterprise and API offerings for businesses. - **Agentic AI**: Building autonomous agents that can “transform work” (announced June 2026). - **IPO preparation**: Confidential S-1 filing indicates intent to go public, which will require increased financial transparency and governance maturity. ## Why Work Here - **Culture & values**: OpenAI’s stated values include “Humanity first,” “Act with humility,” “Feel the AGI,” and “Ship joy.” Operating principles emphasize agency, creativity, rapid iteration, and intense focus. - **Benefits**: Competitive health insurance, mental healthcare support, 24-week paid birth-parent leave (plus 20 weeks for other parents), generous PTO, annual learning & development stipend, daily meals (breakfast, lunch, dinner), and a domestic conference budget. - **Work environment**: Hybrid/office-based (San Francisco headquarters). The company offers a residency program for researchers and engineers transitioning into AI. - **Impact**: Employees work directly on frontier AI models that shape the industry and society. The mission-driven nature attracts talent passionate about AGI’s societal implications. ## Sources 1. [OpenAI About Page](https://openai.com/about/) 2. [OpenAI Careers Page](https://openai.com/careers/) 3. [OpenAI Job Search](https://openai.com/careers/search) 4. [OpenAI Homepage](https://openai.com/) ## Other roles at OpenAI - [Account Director, Digital Natives](https://feeny.ai/job/account-director-digital-natives-openai-delhi-w85camznm9da) — Delhi, India - [Product Designer, Youth](https://feeny.ai/job/product-designer-youth-openai-san-francisco-y2ejwx2gxsn1) — San Francisco, CA - [Senior Manager, EHS - Robotics](https://feeny.ai/job/senior-manager-ehs-robotics-openai-san-francisco-562ppxrm3e6n) — San Francisco, CA - [Hardware Strategic Sourcing Manager, Optics](https://feeny.ai/job/hardware-strategic-sourcing-manager-optics-openai-san-francisco-vrghp3x83twa) — San Francisco, CA - [Research Program Manager, Governance](https://feeny.ai/job/research-program-manager-governance-openai-san-francisco-t9jpag8tgexs) — San Francisco, CA - [Partnerships Operations Lead, OAI for Government](https://feeny.ai/job/partnerships-operations-lead-oai-for-government-openai-washington-vzejrcam99mr) — Washington, DC - [Technical Program Manager, Manufacturing Operations](https://feeny.ai/job/technical-program-manager-manufacturing-operations-openai-singapore-2px9t2t2dyvy) — Singapore - [Creative Director, Copy](https://feeny.ai/job/creative-director-copy-openai-new-york-jd7jgsad5xr4) — New York, NY - [Engineering Manager, ChatGPT Search Infrastructure](https://feeny.ai/job/engineering-manager-chatgpt-search-infrastructure-openai-san-francisco-hh32vszf6wmn) — San Francisco, CA - [Physical Design Engineer, Forward Deployed Engineering](https://feeny.ai/job/physical-design-engineer-forward-deployed-engineering-openai-san-francisco-qqh4c31zzvj5) — San Francisco, CA