Agentic Harness Engineer

About the role

DeepJudge is looking for an Agentic Harness Engineer to shape the core of its AI‑driven legal platform. You will be responsible for turning cutting‑edge language models into reliable, enterprise‑grade features that legal teams can trust every day.

Key responsibilities

• Own the agentic harness that powers critical DeepJudge features.
• Design, implement, and continuously monitor end‑to‑end evaluation pipelines.
• Improve agent performance through code enhancements and prompt engineering.
• Influence model selection and launch decisions based on agent quality metrics.
• Collaborate with Legal Engineering, Product, and Customer Success to prioritize harness improvements.
• Stay up‑to‑date with LLM, GenAI, and agentic AI trends and integrate best practices.

Required profile

• Master’s degree in Computer Science or a related field, or equivalent practical experience.
• Proficiency in one or more backend languages such as Python, Rust, Go, or C++.
• Experience evaluating agentic systems and building robust evaluation frameworks.

Required skills

• Python
• Rust
• Go
• C++