Skip to content

About the role

The team adapts and improves large language models for legal applications. The research engineer designs and executes post-training experiments using supervised fine-tuning and reinforcement learning. This involves developing reward functions, managing large-scale training runs, and evaluating model performance for customer use.

Our summary of the posting; the original is on the Harvey careers page.

What the posting requires

Required
Preferred

These tags are our reading of the posting. They can miss something; the original posting is the reference.

Add your resume

Drop a PDF here, or

PDF or plain text, up to 10 MB.

Nothing is kept until you say so.