Junie is the AI coding agent by JetBrains that can navigate project files, run code, execute terminal commands, and modify the file system autonomously. This project focuses on enhancing Junie’s performance in critical use cases.

This project requires a deep dive into Junie’s AI model and agentic framework, demanding strong research intuition. Key aspects include LLM fine-tuning for superior performance and rigorously evaluating generalization capabilities, across multiple dimensions.

• Proven research publication track record

• Experience with LLM fine-tuning and evaluation, ideally in the coding domain

• Python programming skills