Product Evals Engineer

About the Team

The ChatGPT Learning & Education team is building AI-powered experiences that help people learn, teach, and pursue their curiosity. We work across research, engineering, product, design, and education to make ChatGPT a more effective and trustworthy learning companion for students, educators, and lifelong learners.

Factuality, personalization, and model response quality are central to this mission. Learners need answers that are relevant, accurate, well-supported, appropriately scoped, and responsive to their level of understanding. Our team develops the evaluation systems and insights needed to understand these qualities, identify gaps, and improve the experiences we deliver.

About the Role

As a Product Evals Engineer, you will lead the development of systems that evaluate response quality across ChatGPT’s learning experiences. You will define what excellent responses looks like for learners, translate those principles into measurable criteria, and build the infrastructure needed to evaluate performance at scale.

You will combine human judgment, automated evaluation, experimentation, and deep analysis to uncover quality issues and accelerate iteration. This work will span retrieval, ranking, answer quality, source selection and attribution, and end-to-end user outcomes. You will partner closely with model measurement team, product engineers, data scientists, and education experts to ensure our evaluation methods reflect both technical quality and genuine learning value.

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

In This Role, You Will

• Build and evolve evaluation frameworks for quality, triggering, and information-grounded experiences within ChatGPT Learning.

• Define quality metrics and evaluation criteria for relevance, factual accuracy, source quality, coverage, freshness, citation support, safety, and educational usefulness.

• Develop scalable evaluation pipelines that combine expert human judgment, behavioral signals, model-based grading, and deterministic checks.

• Create representative datasets and benchmarks spanning student, educator, and lifelong-learning use cases.

• Design experiments that identify quality gaps, measure progress, and help teams make informed product and model decisions.

• Analyze evaluation results and user behavior to uncover systematic failure modes, emerging trends, and high-impact opportunities.

• Improve the reliability of automated evaluators through calibration, validation, and ongoing comparison with human judgments.

• Partner with engineering and research teams to translate findings into improvements across retrieval, ranking, model behavior, and product design.

• Build tools that make evaluation results accessible, interpretable, and actionable for teams across the organization.

• Help establish best practices for measuring the quality and learning impact of AI-powered search experiences.

You Might Thrive in This Role If You

• Are a strong software engineer who can design reliable data pipelines, evaluation infrastructure, and internal tools.

• Understand information retrieval concepts and metrics, while recognizing where conventional search metrics may not capture the quality of an AI-generated learning experience.

• Have experience working with human-labeled data, relevance judgments, annotation programs, or model-based evaluation.

• Are comfortable going deep into qualitative and quantitative data to identify subtle issues and systemic patterns.

• Can turn ambiguous product goals—such as trustworthiness or educational usefulness—into clear, testable definitions of quality.

• Communicate technical findings clearly and can influence decisions across research, engineering, product, and nontechnical partners.

• Have a strong intrinsic desire to learn, fill gaps in your knowledge, and share what you discover with others.

• Care deeply about building AI systems that help people learn while remaining accurate, responsible, and worthy of trust.

Nice to Have

• Experience evaluating large language models, retrieval-augmented generation systems, or agentic search products.

• Familiarity with learning science, education technology, assessment design, or educational measurement.

• Experience with causal inference, online experimentation, or analysis of large-scale product telemetry.

• Knowledge of evaluation challenges involving multilingual, multimodal, or age-appropriate learning experiences.

• Experience developing or validating LLM-based graders and other automated evaluation methods.

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 do not discriminate based on race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, gender identity or expression, or any other legally protected status.

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.

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. 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.