Research Intern, Frontier Speculative Decoding (Winter 2027)
EmployerTogether AI
LocationSan Francisco
Pay$58 – $70 per hour
Posted2026-10-16
Confirmed open2026-10-26
Apply on the employer’s site Open in Atlas
About this 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…
Excerpt only. The full posting is on the employer’s careers site.
More jobs at Together AI
- Senior Recruiter, G&ATogether AI · San Francisco · $165,000 – $210,000 per year
- (Senior/Junior AI Inference Reliability Engineer, Compute InfraTogether AI · San Francisco · $160,000 – $280,000 per year
- Technical Writer Intern, Developer Experience (Summer 2027)Together AI · San Francisco · $41 per hour
- Director, Debt Capital MarketsTogether AI · San Francisco · $265,000 – $310,000 per year
- Forward Deployed Engineer, Post-TrainingTogether AI · San Francisco · $270,000 – $300,000 per year