jobs

Research Intern, Inference (Summer 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

In inglese

Company

Together AI

Location

San Francisco

Status

Open

Posted

2026-09-18T15:44:40+00:00

A 12-to-14-week research internship on Together AI's Inference Research team in San Francisco, working on serving systems for large foundation models. Projects span distributed inference, cross-layer optimization across models, systems and hardware, KV cache design, speculative decoding and large-scale serving. The intern runs experiments, reports progress and writes up findings in papers and blog posts. Applicants should be finishing a Bachelor's, Master's or PhD in computer science, electrical engineering or a related field, with PyTorch or JAX and strong Python; CUDA experience and MLSys or ICLR publications are preferred.