Open to opportunities

Michael Nguyen

@michaelnguyen1

Message

Senior Software Engineer building scalable, low-latency AI search and summarization systems.

United States

Message

What I'm looking for

I’m looking to build trustworthy, production-scale AI experiences—scalable retrieval, low-latency search/summarization, and reliable ML/cloud infrastructure—while partnering cross-functionally and mentoring engineers to ship high-impact features.

I’m a Senior Software Engineer with 10+ years of experience leading end-to-end development of AI-powered search and summarization platforms, ML infrastructure, and cloud backend systems at Google and Arbor Networks. At Google, I’ve delivered scalable, low-latency experiences for over a billion users while mentoring engineers to drive execution.

From architecting RAG pipelines with semantic chunking and re-ranking to optimizing LLM context windows and reducing hallucinations, I focus on trustworthy, production-grade AI. I also design high-performance retrieval and vector search systems (including sub-100ms similarity search) and build reliable inference engines, partnering across product, research, and engineering to turn roadmaps into measurable impact.

Experience

Work history, roles, and key accomplishments

Current

Senior Software Engineer

Current

Google

Jan 2021 - Present (5 years 2 months)

Led end-to-end development of AI features for NotebookLM, Maps, and Photos, delivering scalable low-latency search and summarization for 1B+ users. Architected RAG with semantic chunking and re-ranking to reduce hallucinations, optimized LLM context windows to cut inference costs by 30%, and built distributed vector search enabling sub-100ms similarity and Maps workloads at 10k+ requests/sec with

Lang Chain Python PyTorch Triton Inference Server Kafka

Software Engineer

Arbor Networks

Aug 2015 - Dec 2020 (5 years 4 months)

Improved ML model accuracy from 60% to 87% and increased the network-flow collection pipeline throughput by 200% to handle high-volume traffic surges. Built STIX/TAXII backend services and REST APIs for automated data synchronization, and delivered reporting dashboards for real-time enterprise network visibility.

Java Spring Boot fastAPI STIX & TAXII Kafka scikit learn TensorFlow RESTful APIs