Harness Engineer

About the Company

Nomic builds AI agents and developer tools that power the built world. We help enterprise teams in architecture, engineering, and construction extract structured knowledge from decades of drawings, specs, and project files.

Responsibilities

• Develop retrieval systems including search, ranking, chunking strategies, and hybrid approaches
• Implement context engineering to assemble information for agents operating over large, heterogeneous document sets
• Build evaluation harnesses and infrastructure to continuously measure agent accuracy and regression-test retrieval quality
• Design agent pipelines and the orchestration layer between retrieval, models, and downstream actions
• Scale systems to work across thousands of customer document collections

Requirements

• Strong software engineering skills in Python and/or TypeScript
• Real experience with retrieval systems such as embeddings, vector search, or traditional IR
• Experience building systems that handle messy, real-world data
• Practical familiarity with LLMs and agent frameworks
• Systems-thinking approach to component interaction and scalability

Preferred Qualifications

• Experience with evaluation infrastructure, benchmarks, and regression testing for AI systems
• Background in search, NLP, or information retrieval
• Exposure to the AEC industry or other document-heavy domains