Build LLM and coding-agent harnesses, evaluation benchmarks, enterprise Document AI products, and reliable AI systems. Responsibilities include architecture, tool and permission design, automated validation, model experiments, data curation, applied research, production monitoring, and end-to-end product delivery. The role requires strong software engineering, practical LLM experience, extensive coding-agent use, an evidence-driven approach to AI evaluation, and ownership in a fast-moving founding team.

Build and improve cloud and on-premises platforms supporting AI products. Responsibilities include software engineering, infrastructure reliability, scalability, troubleshooting across code, databases, and infrastructure, automation, SLO and error-budget management, security, monitoring, and developer experience improvements. The role collaborates with machine learning, product, and QA teams while driving strategic engineering initiatives.

Lead design, implementation, deployment, and maintenance of production ML systems for document understanding. Build scalable model-serving infrastructure, develop and fine-tune ML models (CV/NLP/OCR), collaborate with product owners, and mentor junior engineers.