Get a reply from this employer
Your resume and cover letter, tailored to exactly what they’re hiring for.
Baseten is seeking a product leader to own the developer-facing side of our high-performance inference platform in San Francisco. You’ll guide how developers find, test, deploy, and operate models in production, balancing speed, quality, and cost.
You’ll translate complex tech work into products developers actually adopt, focusing on API design, tooling, and a smooth UX for experimentation and deployment at scale.
This role owns the developer facing side of an inference platform, covering how people find models, try them, deploy them, and keep them running in production. A strong candidate has deep hands on work with model serving frameworks and a clear grasp of GPU cost and the tradeoffs between speed, quality, and price. They also bring a record of turning technical work into products that developers actually adopt.
Inference is where AI models meet real users, so the work sits close to the cost and reliability questions that decide whether an AI product ships. Much of the routine tuning and benchmarking can be automated, which shifts the product manager toward judgment about which models and workloads matter and how to make the path feel simple. The human part is taste in developer experience and reading what customers find frustrating.
The role offers direct exposure to serving open source and custom models at scale, including evaluation, optimization, and operating them in production. Someone building toward it could deploy models with common serving frameworks, measure latency and throughput against cost, and study how developer tools like APIs and consoles are designed. Working with real inference workloads and reading how teams put models into production would help.
High-performance cloud inference platform for deploying, serving, and scaling open-source and custom artificial intelligence models.