Researcher, Recursive Self-Improvement Safety

OpenAI, Inc.

San Francisco (CA)

Presencial

GBP 120.000 - 180.000

Jornada completa

Hace 11 días

Una candidatura completa en un minuto

Currículum y carta de presentación personalizados, listos para enviar.

Supera los filtros ATS

Descripción de la vacante

OpenAI, Inc. is seeking a Preparedness technical executor to anticipate misalignment risks and develop practical safeguards for advancing AI systems. You will design 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 safety capabilities as models grow.

Formación

  • Strong technical execution and strategic thinking required.
  • Experience in AI safety, risk assessment, or verification is a plus.
  • Ability to communicate complex ideas clearly to cross-functional teams.

Responsabilidades

  • Carefully consider future challenges OpenAI might face and plan accordingly.
  • Translate open-ended objectives into concrete, prioritised actions (e.g. stress-test monitors).
  • Execute quickly with prototyping, then mature into stable safety pipeline components.

Conocimientos

Technical execution
Strategic thinking
AI safety domain knowledge
Communication

Descripción del empleo

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.

Consigue la evaluación confidencial y gratuita de tu currículum.

o arrastra y suelta tu archivo aquí

Similar jobs

Puestos de trabajo similares que vale la pena comparar

Strategic AI Safety Researcher for Recursive Self-Improvement
Strategic AI Safety Researcher for Recursive Self-Improvement

OpenAI, Inc. • San Francisco (CA)

Presencial
USD 180.000 - 240.000
Researcher, Frontier Risk Mitigations
Researcher, Frontier Risk Mitigations

OpenAI, Inc. • San Francisco (CA)

Presencial
GBP 120.000 - 180.000
Researcher, Frontier Cybersecurity Risks
Researcher, Frontier Cybersecurity Risks

OpenAI, Inc. • San Francisco (CA)

Presencial
USD 295.000 - 445.000
Frontier AI Safety Researcher: Mitigations & Alignment
Frontier AI Safety Researcher: Mitigations & Alignment

OpenAI, Inc. • San Francisco (CA)

Presencial
USD 180.000 - 280.000
Software Engineer, Cyber Safeguards
Software Engineer, Cyber Safeguards

OpenAI • San Francisco (CA)

Presencial
USD 250.000 - 350.000
Researcher, Agent Safety, Training and Evaluations
Researcher, Agent Safety, Training and Evaluations

Precision Labs • San Francisco (CA)

Híbrido
USD 180.000 - 240.000
Relocation assistance
Researcher, Safety - Frontier Assurance
Researcher, Safety - Frontier Assurance

OpenAI, Inc. • San Francisco (CA)

Presencial
USD 180.000 - 260.000
Engineering Manager, Preparedness
Engineering Manager, Preparedness

OpenAI, Inc. • San Francisco (CA)

Híbrido
USD 250.000 - 350.000
Relocation assistance
Hybrid work model
Data Scientist, Preparedness
Data Scientist, Preparedness

OpenAI, Inc. • San Francisco (CA)

Presencial
USD 347.000 - 400.000
Researcher, Agent Safety, Training and Evaluations
Researcher, Agent Safety, Training and Evaluations

Society for AI Security • San Francisco (CA)

Híbrido
USD 140.000 - 190.000
Relocation assistance
Hybrid work model