Software engineer with 5+ years of experience building scalable, user-facing products. Specializes in React/TypeScript with full-stack capabilities across Node.js, Python, Go, and AWS. Proven track record of optimizing frontend performance, building secure APIs, and shipping AI/agentic systems including context-aware assistants, MCP servers, and multi-agent orchestration.

Skills

Frontend

TypeScriptReactReduxNext.js

Backend

Node.jsExpress.jsPythonGoC#Java

AI/LLM

Gemini & Claude APIRAGSemantic RetrievalLLM IntegrationModel Context ProtocolMulti-agent SystemsAgentic DevelopmentCopilot CLI

Testing

JestPlaywright

Data

MongoDBPostgreSQLRedis

Cloud/DevOps

DockerAWS EC2AWS S3AWS CloudFrontElastic BeanstalkCodePipelineElastiCache

Work Experience

Software Engineer

Microsoft - Vancouver

Jan 2022 - Present

  • Built an end-to-end LLM summarization pipeline for enterprise dashboards, owning backend data ingestion, prompt-tuning layers, and frontend rendering of AI-generated insights for CxO-level users
  • Implemented collaboration-pattern visualization tools with TypeScript and React, enabling org-change impact analysis across multiple dimensions for organizations with millions of employees
  • Optimized frontend rendering performance for complex data visualizations (200k+ links) by implementing data pruning and lazy loading, reducing graph render time from 17s to 2s (an 88% improvement)
  • Designed and drove org-wide adoption of a higher-order component abstraction for the Copilot Dashboard, authoring the design doc and developer guide used to onboard 10+ engineers; standardized query construction, validation, batching, and response consolidation, cutting per-feature development time by 1–2 days
  • Built accessibility and telemetry into every client-side feature as design-time requirements, configuring alerts that automatically raise incident tickets when API failure rates exceed healthy thresholds
  • Integrated agentic AI tools into daily development across building, testing, and code review, verifying AI-generated changes against automated Playwright end-to-end tests before anything reaches production
  • Partnered with UX designers and product managers in cross-functional teams to transform user feedback into priority features

Full Stack Engineer

Scotiabank - Vancouver

Apr 2021 - Dec 2021

  • Developed a React web application enabling real-time loan approval decisions, backed by scalable and secure REST APIs built with Node.js and Express
  • Achieved 90%+ code coverage through comprehensive unit and integration testing with Jest

Full Stack Engineer

MeaningfulWork Inc - Vancouver

Sep 2020 - Mar 2021

  • Engineered a full-stack React application, provisioning highly available AWS infrastructure (EC2 auto-scaling, S3, CloudFront) to optimize global asset delivery

Personal Projects

Zazu Multi-Agent System

2026

  • Built a process-isolated multi-agent system with LLM-based intent routing and cross-agent communication through a shared database event bus
  • Designed a critic loop that classifies failures, controls retry behavior, and stops expensive execution paths before they exceed cost ceilings
  • Implemented retrieval-augmented memory, injecting sqlite-vec semantic recall into agent prompts before each answer, with expiring context, cross-domain recall, human-in-the-loop approval paths, prompt-injection checks, and checkpointing

Distributed AI-Powered Personal Website

2026

  • Built a context-grounded conversational assistant that answers questions about my background using local resume, project, and bio content
  • Designed a distributed microservices architecture (Next.js, Go API Gateway, Python/FastAPI) with Gemini streaming responses and in-memory rate limiting

MCP Servers — Portfolio Tracker & Music Discovery

2025

  • Developed custom MCP servers (TypeScript/Node.js) enabling LLM-native interfaces for investment portfolio tracking and Discogs collection management
  • Use the portfolio tracker to manage my own multi-account USD/CAD investment portfolio, recording trades, tracking ROI, and comparing portfolio snapshots through natural-language queries in Claude, with holdings valued on demand at the latest market prices
  • Integrated external REST APIs with Claude tooling to enable natural language querying and contextual data injection for local AI agents

Education

Master of Engineering, Mechanical Engineering

University of California, Berkeley

2019

Awards

US Patent (pending)

Co-inventor of an enterprise data visualization and rendering architecture at Microsoft

Hackathon Winner (x2)

Won back-to-back Microsoft org-level hackathons as the sole frontend developer, rapidly prototyping streamlined UX flows that simplified complex report querying and accelerated data retrieval

Certifications

AWS Certified Solutions Architect - Associate (2021)