jobs
Research Intern, Frontier Speculative Decoding (Summer 2027)
About the Role The Speculative Decoding team at Together AI builds the draft models and algorithms that let large language models generate faster without changing their outputs.
En inglés
- Company
- Together AI
- Location
- San Francisco
- Status
- Open
- Posted
- 2026-10-16 22:48 UTC
Together AI's Speculative Decoding team seeks a research intern to work on draft models and algorithms that make large language model generation faster. The intern will prototype decoding methods and drafter architectures, train and distill draft models on dedicated GPU clusters, test ideas against realistic serving workloads, and help move successful work into production. The posting asks for a master's or PhD student in computer science, electrical engineering or a related field, with deep-learning fundamentals and distributed-training experience such as Megatron-LM or FSDP. The internship is on-site in San Francisco.
Original job posting