Labs Fellowship

Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, Open Evidence, Abridge, Clay, Gamma and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F, led by Altimeter Capital, Conviction Partners, and Spark Capital.

Join us and help build the platform engineers turn to to ship AI products.

Base Labs is a research lab pushing the frontier of open-source LLMs. We think intelligence should be democratized, not controlled by a handful of closed labs and we think very few teams are actually positioned to do something about that. Backed by Baseten's training and inference infrastructure, we have the compute, resources, and talent to take on hard problems at the frontier and open-source what we learn along the way.

Our mission is to help build a world where intelligence isn't concentrated, but spread across an ecosystem of models that anyone can build on. That mission shapes what we choose to work on, how we work on it, and who we want in the room. We are accepting applications on a rolling basis for our first cohort of Base Labs Fellows, which is expected to start in late September.

The Base Labs Fellowship is designed to give researchers exposure to what frontier research looks like in industry. We provide funding, mentorship, and full support to our fellows, with the goal of producing rigorous, published research that shapes both the open-source ecosystem and Baseten's technical roadmap.

We run multiple cohorts of Fellows each year and review applications on a rolling basis. This application is for cohorts starting in Sept 2026 and beyond.

• 3 months of full-time research from our San Francisco office
• A dedicated 1:1 mentorship from a senior researcher
• $15,000 Stipend (per 3-months)
• Funding for compute and other research expenses
• Opportunities to publish and present at top venues, including ICML, NeurIPS, and Grace Hopper
• A clear path to a full-time offer for the strongest performers

Each fellow is matched 1:1 with one of three senior researchers.

Potential mentors include:

• Michael Psenka
• Max Kirkby
• Charles O’Neill

A quick note on our view on talent.

Many of the labs that exist today run a credentialist talent model. Concentrate the most already-legible researchers, and assume the concentration compounds. The best researchers in this field are very often not yet legible. Research engineers who have spent years inside a production stack and developed insights no PhD program teaches;
PhDs working on the wrong-shaped problem at the right-shaped lab; operators w