• Design, build, and deploy AI applications and agentic workflows using Python, LangChain, and LangGraph.

• Architect multi-agent systems and tool-augmented LLM pipelines to automate complex business processes.

• Develop and maintain reusable AI skills and components to enable rapid assembly of new AI features. • Apply prompt engineering best practices to improve LLM performance, consistency, and output quality.

• Champion harness engineering: build test harnesses and evaluation frameworks to systematically measure and improve AI system quality.

• Design and maintain data pipelines and ETL processes to ensure data is clean, timely, and suitable for AI systems. • Implement data quality standards and monitoring to ensure the reliability of data flowing into AI workflows.

• Collaborate with product and business stakeholders to translate requirements into working AI solutions.

• Monitor production AI systems, identify failure modes, and drive continuous improvement.

• Stay current with the AI landscape and proactively introduce improvements to our stack.

• 5+ years of software development experience, with at least 2 years in AI/LLM application development.

• Strong Python proficiency — clean, testable, production-quality code.

• Hands-on experience with LangChain and LangGraph for building agentic workflows.

• Experience with prompt engineering and LLM output structuring.

• Experience building test harnesses or evaluation frameworks for AI systems.

• Solid engineering fundamentals: Git, testing, CI/CD, code review.

• Experience with data pipelines, ETL processes, and data quality management.

• Bachelor's degree or higher in Computer Science or a related field.