About the job
ABOUT BASETEN
Baseten is at the forefront of AI innovation, providing essential inference solutions for leading AI companies such as Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma, and Writer. By integrating advanced AI research with adaptable infrastructure and top-notch developer tools, we empower companies on the cutting edge of AI to deploy state-of-the-art models effectively. Our rapid growth is underscored by our recent $300M Series E funding from prominent investors including BOND, IVP, Spark Capital, Greylock, and Conviction. Join us in shaping the platform that engineers rely on to launch AI products.
THE ROLE:
As voice becomes the next significant interface on the internet, building a production-grade Voice AI system is a challenging endeavor. You will be part of a pioneering team within Baseten Voice AI, dedicated to deploying cutting-edge open-source models for clients in sectors such as productivity, customer service, clinical dialogue, creator tools, education, and beyond. Your work will make a profound difference in everyday lives and contribute to transforming various industries.
This role is characterized by high impact and substantial ownership. You will take the lead on Baseten Voice AI, overseeing our proprietary inference stack that powers Voice AI models, from product roadmap to engineering execution. You will collaborate closely with Forward Deployed Engineers, Model Performance Engineers, and other engineering teams to redefine the limits of Voice AI.
EXAMPLE INITIATIVES:
The world's fastest Whisper — with streaming and diarization
Work with the Core Product team to develop an orchestration framework for a multi-model voice agent
Partner with the Training Platform team to facilitate ongoing training of voice models
Create an intuitive, developer-friendly API and SDK to promote self-service adoption of Baseten Voice AI products.

