LLM Research Intern: Agent RL Training & Innovation

GoTo Meeting; Mountain View (CA); On-site; USD 48,216 - 68,880; Part time

Job summary

NewsBreak in Mountain View, CA is hiring a Research Intern for their Agent RL Training team. The role involves collaboration with a mentor to drive research on applying large language models to core business operations. Responsibilities include running SFT experiments, curating training datasets, and contributing to public publications.

Ideal candidates are research-driven individuals with strong Python and PyTorch skills. The internship offers an hourly pay between $35 and $50.

Qualifications

• Willing to put in extra hours to push projects across the finish line.
• Genuine passion for research, reads papers, and tinkers with models.
• Independently capable of end-to-end model SFT.

Responsibilities

• Collaborate with mentor to identify research directions for applying LLMs.
• Run end-to-end SFT experiments on LLM-based agents.
• Contribute to public publications during your internship.

Skills

Python

PyTorch

Research motivation

End-to-end model SFT

Tools

CUDA

Triton

OpenRLHF

Job description

NewsBreak in Mountain View, CA is hiring a Research Intern for their Agent RL Training team. The role involves collaboration with a mentor to drive research on applying large language models to core business operations. Responsibilities include running SFT experiments, curating training datasets, and contributing to public publications.

Ideal candidates are research-driven individuals with strong Python and PyTorch skills. The internship offers an hourly pay between $35 and $50.