Research Intern — LLM Agents & RL Training

NewsBreak; Mountain View (CA); On-site; USD 48,216 - 68,880; Full time

Job summary

NewsBreak is seeking a Research Intern to join their Agent RL Training team in Mountain View, CA. In this hands-on role, you will work closely with a mentor to apply large language models to impactful projects, driving experiments and contributing to publications.

The ideal candidate is passionate about research, independent, and skilled in Python and PyTorch. Compensation ranges from $35 to $50 per hour based on experience.

Qualifications

• Highly motivated and committed, willing to put in extra hours when needed.
• Genuine passion for research and model experimentation.
• Capable of end-to-end model SFT with understanding of RL-based methods.
• Strong reasoning about effective model behavior.

Responsibilities

• Collaborate with a mentor on research directions for applying LLMs.
• Run end-to-end SFT experiments on LLM-based agents.
• Curate high-quality training datasets.
• Contribute to public publications.

Skills

Strong Python

PyTorch skills

Research passion

Independent problem-solving

Job description

NewsBreak is seeking a Research Intern to join their Agent RL Training team in Mountain View, CA. In this hands-on role, you will work closely with a mentor to apply large language models to impactful projects, driving experiments and contributing to publications.

The ideal candidate is passionate about research, independent, and skilled in Python and PyTorch. Compensation ranges from $35 to $50 per hour based on experience.