What are the responsibilities and job description for the Engineering Manager, Production Inference position at OpenAI?
About the Team
The Production Inference team is responsible for delivering scalable, efficient, and reliable inference systems for OpenAI's production models, including ChatGPT, API, Search and many more products. Our mission is to provide inference solutions that empower various product teams to bring AI features to our customers and users efficiently and effectively.
About the Role
We are seeking an experienced engineering manager to lead the Production Inference team. In this role, you will bridge the gap between our inference stack and production teams, ensuring seamless deployment of AI models, unlocking model capabilities, while maintaining high performance and reliability. As well as building inference systems that meet the need for both internal and external users. This position requires a seasoned leader with a pragmatic approach to applied AI.
In this role, you will :
Partner with production teams to develop performant, reliable inference solutions for their products.
Partner with research teams to bring their research work into production.
Define and execute technical roadmaps to support model deployment and inference at scale.
Provide strong technical leadership, focusing on applied AI solutions for product inference needs, while ensuring high-performing, collaborative team dynamics.
You might thrive in this role if you :
Are highly technical.
Have 10 years of experience in ML model serving, ML infrastructure, or applied AI, with 5 years in engineering management.
Possess a strong background in ML inference, production AI systems, and distributed systems.
Have experience in building high-scale, high-reliability production AI systems.
Are an effective collaborator, capable of aligning technical, research and business stakeholders to drive impactful solutions.
Have experience leading high performing teams with a focus on scaling and fostering a culture of inclusion and performance.
Thrive in fast-paced environments with evolving priorities and ambitious goals, with the ability to work closely with technical and non-technical stakeholders.
