Research Intern RL & Post-Training Systems, Turbo (Summer 2026)

Together AI(29 days ago)

San Francisco, CAOnsiteInternshipIntern$116,000 - $126,000Research

About this role

A research intern on the Turbo Research team studying how to make post-training and reinforcement learning for large language models efficient, scalable, and reliable. The role focuses on co-designing algorithms and inference/training systems to enable larger experiments, longer rollouts, and more realistic evaluations. This is a summer internship program lasting 12 weeks with defined date ranges.

View Original Listing

Required Skills

Reinforcement Learning
Post-Training
ML Systems
Inference Systems
Empirical Research
Experiment Design
Python
C++
CUDA
Distributed Systems

+2 more

Qualifications

PhD in Computer Science or EE
MS in Computer Science or EE

About Together AI

together.ai

Together AI is an "AI Native Cloud" that helps teams reliably build, deploy, and scale AI-native applications. It combines cutting‑edge research with a complete developer experience and infrastructure optimized for high price‑performance. Together provides hosted model training and inference, APIs/SDKs, and tooling to move projects from experimentation into production. Customers pick it for scalability, cost efficiency, and faster time-to-production for AI applications.