Research Engineer, Post-Training Evals

About the Team

The Post-Training team is responsible for training and improving pre-trained models to be deployed into ChatGPT, the API, and future products. The team partners closely with research and product teams across the company, and conducts research as a final step to prepare for real world deployment to millions of users, ensuring that our models are safe, efficient, and reliable.

About the Role

We are seeking a Research Engineer/Scientist to help us deeply understand and improve the capabilities of our models through rigorous evaluation, analysis, and experimentation. In this role, you will lead efforts to correlate evaluation metrics with model behavior, user experience, and real-world performance. Your work will directly inform model development, guide research priorities, and ensure that our evaluation methodologies accurately capture the nuanced capabilities.

You will collaborate closely with researchers, data scientists, and engineers to develop robust experimental methodologies, create high-quality evaluation datasets, and design new metrics that capture nuanced aspects of model quality. Your work will bridge the gap between raw metrics and meaningful insights, helping us understand the broader capabilities and limitations of our models.

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, you will:

• Investigate the relationship between evaluation metrics and model behavior:
  Design and execute studies to understand how various metrics correlate with user satisfaction, task success, and broader model capabilities.

• Develop novel evaluation methodologies:
  Create experimental frameworks and evaluation methods to measure complex model attributes, including alignment, robustness, and generalization.

• Collaborate cross-functionally:
  Work with data scientists to analyze user interactions, partner with research teams to implement evaluations and inform model development.
  

You might thrive in this role if you:

• Have a deep understanding of RL or LLMs

• Have a working knowledge of relevant models, and building evaluations for model capability improvement.

• Are comfortable diving into a large ML codebase to debug.

• Thrive in a dynamic and technically complex environment.

• Are excited to explore the capabilities and limitations of cutting-edge AI models.

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 on the basis of race, religion, national origin, gender, sexual orientation, age, veteran status, disability or any other legally protected status. 

OpenAI Affirmative Action and Equal Employment Opportunity Policy Statement

For US Based Candidates: Pursuant to the San Francisco Fair Chance Ordinance, we will consider qualified applicants with arrest and conviction records.

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.