Software Engineering Intern (2026 Grads Only)

As an intern at Baseten, you’ll work on real projects and contribute to systems and products that help our users ship their ML products. You won't be off in a corner doing "intern work" – we're moving too fast and have too much to build for that. Instead, you'll receive hands-on support and mentorship to help you grow fast and make a real impact quickly.

Engineering interns can join one of our four teams:

Core Product: You’ll help build the core Baseten developer workflows that enable users to get value out of ML models. The Core Product team is at the forefront of new product development across a large surface area, including model APIs, training, and dedicated deployment.

Forward Deployed Engineering: You will partner closely with our customers to understand their problems and engineer ML solutions. This role provides a unique front-row view into the opportunities and challenges facing companies implementing ML and AI solutions at scale.

Model Performance: You will implement, refine, and productionize cutting-edge techniques (e.g. quantization, speculative decoding, KV cache reuse, chunked prefill, and LoRA) for ML model inference and infrastructure.

Infrastructure: You'll architect and support development of our ML inference platform that powers production AI applications. You'll make technical decisions for the infrastructure enabling developers to deploy, scale, and monitor ML models with high performance and reliability.

Please Note: Applicants must be a year or less away from graduating.