Open to opportunities

Michael User

@michaeluser23

Message

Senior software engineer specializing in AI-driven systems and scalable backends.

United States

Message

What I'm looking for

I'm seeking senior engineering roles where I can lead development of AI-driven backends, mentor teams, build scalable, HIPAA-compliant systems, and deliver measurable product impact in collaborative, fast-paced environments.

I'm a Senior Software Engineer with 10+ years building web, backend, and AI-driven systems. At Amazon I led delivery of AI document automation (OCR, classification, entity extraction, LLM-assisted drafting), an ASR/NLU/TTS voice agent, a chat-based document assistant, and a chart copilot that reduced rework and improved workflows.

As a founding engineer at Navan I launched an end-to-end booking platform, built and operated scalable backend services, optimized APIs with vector embeddings and anomaly detection, and implemented automated tests and CI/CD enabling daily deploys. I prioritize production-ready, compliant solutions and collaborative problem solving across cross-functional teams.

Experience

Work history, roles, and key accomplishments

Senior Software Engineer

Amazon

Mar 2020 - Mar 2025 (5 years)

Implemented an AI document-automation system combining OCR, classification, entity extraction, and LLM-assisted drafting with human review and e-signature to speed submissions and reduce rework. Built ASR/NLU/TTS voice agents, a chat-based document assistant, and a chart copilot, and optimized billing workflows with coding guidance and quality gates while ensuring HIPAA compliance and full auditab

Python AWS NLU LLMs)Chatbot Development HIPAA CI CD

Founding Engineer

Navan

Aug 2015 - Jan 2020 (4 years 5 months)

Launched an end-to-end enterprise booking platform and operated scalable backend services for bookings, policy enforcement, payments, and expenses to ensure high availability and low latency. Improved API performance via smart batching, connection pooling, and cache invalidation, enhanced search with vector embeddings and anomaly detection, and achieved production readiness with automated tests an