Stephen Koo
@stephenkoo
Senior software engineer specializing in scalable AI infrastructure and production LLM integrations.
What I'm looking for
I am a Senior Software Engineer with over eight years of experience designing and operating scalable backend and AI infrastructure systems for large-scale production environments.
At Google, I led design and implementation of AI inference orchestration, routing, and caching layers (Golang, Go on GKE), delivering measurable latency reductions and multi-region high availability for Gmail and Google Chat.
I build end-to-end solutions spanning services, CI/CD, observability, and front-end experiences using React/TypeScript and Next.js, and I productionize LLM-backed features with Kubernetes, Vertex AI/Gemini, and retrieval-augmented generation.
I partner cross-functionally with ML, product, and privacy teams, mentor engineers, and focus on reliability, performance, and enterprise-grade AI capabilities that drive product impact.
Experience
Work history, roles, and key accomplishments
Led the design and implementation of the AI Inference Orchestration Service (Golang), a critical component responsible for routing requests between Workspace surfaces and ML models. Optimized the Golang request batching layer and implemented in-memory caching strategies, contributing to a team-wide 30% reduction in P95 inference latency
Education
Degrees, certifications, and relevant coursework
Stanford University
Master of Science, Computer Science (Artificial Intelligence)
2015 - 2017
Completed a Master of Science in Computer Science with a focus on Artificial Intelligence, covering advanced AI topics and research-driven coursework.
Stanford University
Bachelor of Science, Computer Science (Artificial Intelligence)
2011 - 2015
Completed a Bachelor of Science in Computer Science with a focus on Artificial Intelligence, including foundational coursework in algorithms, systems, and AI.
Tech stack
Software and tools used professionally
JDA
GitHub
Kubernetes
GitHub Actions
MySQL
PostgreSQL
MongoDB
Shopify
Gmail
Node.js
Spring Boot
Next.js
Tailwind CSS
Google Analytics
Neo4j
Redis
Terraform
React
Webpack
JavaScript
Python
Java
TensorFlow
PyTorch
Kafka
RabbitMQ
Prometheus
Datadog
Google Workspace
Gemini
Elasticsearch
AWS Lambda
Webflow
TypeScript
JUnit
Docker
Airflow
SQL
Google Kubernetes Engine
LangChain
Plane
Cursor
GitHub Copilot
Remote
Availability
Location
Authorized to work in
Social media
Job categories
Skills
Interested in hiring Stephen?
You can contact Stephen and 90k+ other talented remote workers on Himalayas.
Message StephenFind your dream job
Sign up now and join over 100,000 remote workers who receive personalized job alerts, curated job matches, and more for free!
