Kevin Pang

I’m a Senior Full-Stack AI Software Engineer with 10+ years of experience designing, developing, and deploying scalable web, backend, cloud-native, and AI-powered applications. I specialize in production-grade Generative AI solutions using TypeScript, Python, React, Node.js, AWS, and modern AI technologies.

I’ve designed enterprise AI applications leveraging Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI Agents, and Model Context Protocol (MCP). I build secure, reliable systems—integrating vector search, prompt engineering, structured outputs, and function calling—so outputs are grounded and maintainable.

In my recent work, I’ve delivered cloud-native infrastructure and scalable backend services with AWS, Docker, Kubernetes, Terraform, and CI/CD pipelines. I focus on performance through caching strategies, asynchronous processing, and scalable distributed architecture.

Some highlights include transforming unstructured sales-call transcripts into structured deal briefs in under one minute, delivering streaming AI responses in under 2 seconds, and reducing inference costs to approximately $0.03 per transcript through efficient model orchestration. I’m passionate about shipping high-quality software that solves complex business challenges.