Research Intern, Agent Rl Training

News Break

Mountain View, California, United States
Base: $35-$50 usd ph; bonus/equity: not specified;...
On-site
End-to-end model sft experience
Strong python and pytorch skills
Understanding of rl-based post-training methods
This role involves exploring how to apply large language models to NewsBreak's core business including content understanding and autonomous task completion

Job Summary

  • This role involves exploring how to apply large language models to NewsBreak's core business including content understanding and autonomous task completion.
  • Interns are expected to independently drive experiments, propose novel ideas, and iterate quickly on LLM post-training and agent capabilities.
  • The team supports interns in contributing to public publications and encourages submissions to top-venue conferences during the internship.

Matching Summary

This role involves exploring how to apply large language models to NewsBreak's core business including content understanding and autonomous task completion.

Salary

Base: $35-$50 USD per hour; Bonus/Equity: Not specified; Benefits: Not specified

Skills & Requirements

Must-have

  • End-to-end model SFT experience
  • Strong Python and PyTorch skills
  • Understanding of RL-based post-training methods
  • Ability to reason about model behavior

Nice-to-have

  • Publication at top-tier venue
  • Experience with multi-node distributed training
  • Proficiency in custom GPU kernels
  • Genuine passion for research papers

Key Requirements

  • Highly motivated and committed
  • Genuine passion for research
  • Independently capable of end-to-end model SFT

Work Rights

Not specified

Tailored Resume

Cover Letter