Research Intern RL & Post-training Systems, Turbo (fall 2026)

Together AI Together AI · Data AI · San Francisco, CA · Research

Research intern focused on making post-training and reinforcement learning for large language models efficient, scalable, and reliable, by co-designing algorithms and systems at the intersection of RL, inference, and large-scale experimentation.

What you'd actually do

  1. study RL and post-training methods whose performance and scalability are tightly coupled to inference behavior, co-designing algorithms and systems rather than treating them independently
  2. unlock new regimes of experimentation—larger models, longer rollouts, and more complex evaluations—by rethinking how inference, scheduling, and training interact

Skills

Required

  • PhD or MS in Computer Science, EE, or a related field (exceptional undergraduates considered)
  • research experience in RL algorithms, inference systems, or large-scale experimentation
  • comfortable with empirical research by designing controlled experiments
  • interpreting noisy results and drawing principled conclusions
  • can work across abstraction layers

Nice to have

  • Publications at leading ML and NLP conferences (such as NeurIPS, ICML, ICLR, ACL, or EMNLP)
  • Understanding of model optimization techniques and hardware acceleration approaches
  • Contributions to open-source machine learning projects

What the JD emphasized

  • post-training
  • reinforcement learning
  • inference behavior
  • inference systems
  • large-scale experimentation
  • cost and structure of inference dominate overall training efficiency

Other signals

  • RL algorithms
  • inference systems
  • large-scale experimentation
  • post-training
  • reinforcement learning