Together AI logo for Research Intern, Frontier Speculative Decoding (Summer 2027) job on DevsUnite

Research Intern, Frontier Speculative Decoding (Summer 2027)

Together AI

Actively HiringInternship
Apply
Location

San Francisco

Experience

0-2 years

Role

Research Intern, Frontier Speculative Decoding (Summer 2027)

Salary

Competitive

Share this job

Know someone who'd be a great fit?

Job Description

Role Overview

The Speculative Decoding team at Together AI builds draft models and algorithms that enable large language models to generate faster without altering outputs. As a research intern you will investigate open problems in speculative decoding—including new drafter architectures, verification schemes, knowledge distillation, and traffic‑adaptive drafters. You will train and fine‑tune draft models at scale on dedicated GPU clusters and evaluate them against realistic serving workloads such as long‑context and agentic traffic.

Responsibilities

  • Research and prototype efficient speculative decoding algorithms and draft model architectures.
  • Train, fine‑tune, and distill draft models while designing rigorous experiments to validate hypotheses.
  • Implement optimized versions for serving engines to demonstrate efficacy in real‑world workloads.
  • Communicate project plans, progress, and results to the broader team.
  • Share findings via technical write‑ups and blog posts and help move successful ideas into production.

Requirements

  • Currently pursuing a Master’s or Ph.D. in Computer Science, Electrical Engineering, or a related field.
  • Strong knowledge of Machine Learning and Deep Learning fundamentals.
  • Hands‑on experience training or fine‑tuning large models with distributed training frameworks (e.g., Megatron‑LM, FSDP).
  • Familiarity with modern model architectures such as Mixture‑of‑Experts and hybrid attention.

Required Skills

Machine LearningLLMsDeep Learningspeculative-decodingdistributed-training

Ready to apply for Research Intern, Frontier Speculative Decoding (Summer 2027)?

See how you stack up at Together AI before you apply, or go straight to the application.

Apply Anyway