Agentic Harness Engineer

About the Company

DeepJudge helps legal teams unlock and apply the knowledge inside their organizations through world-class enterprise search and AI infrastructure. Founded by former Google search engineers, our platform is trusted by many of the world’s leading law firms to make institutional expertise instantly available and actionable.

Responsibilities

• Owning the agentic harness powering critical features across DeepJudge
• Building and running the evals end-to-end, from design to instrumentation to continuous monitoring
• Improving agent quality through both code (harness) changes and prompting
• Influencing model and launch decisions from the agent quality standpoint
• Working closely with Legal Engineering, Product, and Customer Success to shape and prioritize harness improvements
• Staying current on LLM, GenAI, and agentic AI trends to incorporate insights into best practices

Requirements

• Master’s degree in Computer Science or a related field, or equivalent practical experience
• Proficiency in Python, Rust, Go, or C++
• Experience evaluating agentic systems and designing meaningful eval frameworks
• Strong interest in the latest trends in GenAI and frontier models
• Proven experience building large applications based on LLMs
• Ability to build from scratch with minimal supervision

Preferred Qualifications

• Experience with agentic SDKs
• Familiarity with the evaluation of LLM-based systems