Research Intern, Frontier Speculative Decoding (Summer 2027)

About the role

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. Our speculators run in production on frontier open models such as DeepSeek, Kimi and GLM. Our work sits at the intersection of model training, inference algorithms and serving systems, and we co-design all three to lower the cost and latency of generation. As a research intern, you will dive into open questions in speculative decoding: new drafter architectures and verification schemes, knowledge distillation and training recipes that align draft and target models, and drafters that adapt as traffic shifts. You will train and fine-tune draft models at scale on dedicated GPU clusters, and test your ideas against realistic serving workloads, including long-context and agentic traffic. Projects aim to answer important research questions in speculative decoding, enabling faster generation on frontier models, drafters that keep pace with changing workloads, and robust, reproducible evaluation under real traffic. Past Research Speculative decoding research by Together researchers, interns and academic…

This is a summary of the advert. The full description and the application are on Together AI's careers site.

More roles at Together AI

• Engineering Manager, Kubernetes Bare Metal InfrastructureSan Francisco
• Senior Web & Inbound Growth ManagerSan Francisco
• Strategic Account Executive Inference IndiaIndia
• Sr. Field Marketing & Community ManagerNew York
• Sr. Field Marketing & Community Manager, EMEALondon
• Event & Field Marketing SpecialistSan Francisco
• (Senior/Junior AI Inference Reliability Engineer, Compute InfraSan Francisco
• Senior Recruiter, G&ASan Francisco