jobs

Research Intern, Inference (Winter 2027)

About The Role The Inference Research team is dedicated to building the next generation of efficient, scalable, and reliable serving systems for large foundation models, directly contributing to the mission of advancing open and transparent

Company

Together AI

Location

San Francisco

Status

Open

Posted

2026-09-18T15:44:47+00:00

Together AI's Inference Research team is hiring a winter research intern to work on serving systems for large foundation models. Projects cover distributed inference, compiler-aware optimization, and inference-time strategies such as speculative decoding, with cross-layer co-design across models, systems and hardware, including KV cache design. Applicants should be final-year bachelor's, master's or PhD students in computer science or electrical engineering, with deep learning fundamentals, PyTorch or JAX experience, Python and Transformer knowledge. The 12–14 week internship runs January 4 to April 9 and expects published write-ups of results.