Figure model serp_jobs.h1.location_city

About the Team

The Safety Systems team is at the forefront of OpenAI's mission to build and deploy safe AGI, driving our commitment to AI safety and fostering a culture of trust and transparency.

The Model Policy team aligns model behavior with desired human values and norms. We co-design policy with models and for models. Key focus areas include : addressing critical societal challenges like info-hazard risks and how the model should respond in mental health contexts; defining evaluation criteria for foundational models ability to reason about safety, values, and questions of cultural norms; and driving rapid policy taxonomy iteration based on data.

About the Role

Providing access to powerful AI models introduces a host of challenging questions when it comes to model safety : How do we define safe behavior for how a model should behave? To what end? How do we do this in such a way that is actionable, objective and sustains replicability?

This is a senior role in which youll help shape policy creation and development at OpenAI and make an impact by helping ensure that our groundbreaking technologies do not create harm. The ideal candidate can identify and develop cohesive and thoughtful taxonomies of harm on high risk topics with a sense of urgency. They can balance internal and external input in making complex decisions, carefully think through trade-offs, and write principled, enforceable policies based on our values. Importantly, this role is embedded in our research teams and directly informs model training.

This role is based in San Francisco, CA. We use a hybrid work model of 3 days in the office per week and offer relocation assistance to new employees.

In this role, youll :

Design model policies that govern safe model behavior in an objective and defensible way - e.g. how should the model respond in risky / unsafe scenarios? What does unsafe mean?

You will develop taxonomies that inform data collection campaigns, model behaviour and monitoring strategies and also toe the line between maximizing utility and preventing catastrophic risk.

Lead prioritization for safety efforts across the company for new model launches, understanding and addressing technical and business trade-offs.

Develop a broad range of subject matter expertise while maintaining agility across topics.

You will work across many internal teams which will require high organizational acumen and confident decision making.

You might thrive in this role if you :

Have extensive experience researching LLMs, ML, AI, tech policy, moral reasoning, and / or enjoy classification problems.

Have extensive experience defining, refining and enforcing policies for ML models.

Deeply understand the operational challenges of enforcing policies with RLHF and can incorporate this into policy design.

Can analyze the benefits and risks of open-ended problem spaces; can generate ideas required to solve ambiguous problems and take full ownership of the solution.

Most relevant publications :

Introducing HealthBench

Preparing for future AI capabilities in biology

Safety evaluations hub

OpenAI o1 System Card (Section 3)

GPT-4o System Card (Section 3)

GPT-4 System Card (Sections 2,3,4)

Evaluating Fairness in ChatGPT

Improving Model Safety Behavior with Rule-Based Rewards

OpenAI Model Spec

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 OpenAIs Affirmative Action and Equal Employment Opportunity Policy Statement .

Qualified applicants with arrest or conviction records will be considered for employment in accordance with applicable law, including the San Francisco Fair Chance Ordinance, the Los Angeles County Fair Chance Ordinance for Employers, and the California Fair Chance Act. 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.

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.