Rolewise

Research Intern, Frontier Speculative Decoding (Summer 2027)

Together AI · San Francisco · Office location (mode not stated)

USD 58–70 / hour

Apply on the employer's site ↗
Company
Together AI
Location
San Francisco
Work mode
Office location (mode not stated)
Open to applicants from
On-site/hybrid: local candidates
Level
Fresher / entry
Employment
Internship
Field
Healthcare & Science / Research scientist
Stated pay
USD 58–70 / hour
Posted
2026-10-16 (30 days ago)
Visa sponsorship mentioned
Not mentioned
Listing source
Greenhouse

Machine learningLLMSalesforce

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…

Excerpt only. Read the full description and apply at the original posting on Greenhouse. We list jobs from public job-board feeds and do not alter employer content beyond this excerpt.

Similar roles