Jeffrey SaeleeRésumé

Impact

daily transactions migrated to MongoDB
1M+
query latency after the migration
10s → <1s
better relevance in LLM-generated code
30–40%
AI & full-stack projects shipped in 2026
8

Selected work

Kindred

Code

Multi-agent caregiver assistant · Google × Kaggle AI Agents Intensive capstone

Helps family caregivers manage scheduling and medication for elderly relatives. A local LLM keeps private health data on the machine; the model plans, and deterministic Python validates and executes behind human approval gates.

  • Python
  • Google ADK
  • MCP
  • RAG
  • Local LLM (Gemma)
  • React
  • TypeScript

Pokémon TCG Battle Agent

Competition

Game-playing agent on a live ladder · Kaggle Pokémon TCG AI Battle Challenge

A CPU-only agent that layers determinized Monte Carlo search over a heuristic core, with p99 move time under 0.2 ms. Tuned through 45+ gated experiments (paired A/Bs, SPRT, Wilson bounds) to a peak ladder rating of 972.

  • Python
  • Monte Carlo search
  • Imitation learning
  • Self-play RL

OTTR

Code

AI agent trading system

A crypto trading desk run by seven autonomous agents that meet, debate and vote in Discord. Semantic memory recalls past meetings, and a risk engine enforces stop-losses, drawdown breakers and position caps.

  • React
  • FastAPI
  • Discord.py
  • LM Studio
  • CoinGecko/Kraken APIs

Memora

Code

Full-stack flashcard learning platform

Turns PDF, text and Markdown notes into atomic flashcards with an AI parser, behind a 3D flip-card UI. Supports OpenAI, Gemini and Ollama, with stateless HMAC-SHA256 auth.

  • Java 17
  • Spring Boot
  • React
  • Vite
  • Apache PDFBox

More projects

Experience

Software Engineer at Apple Inc.

Aug 2022 – Sep 2025

Contract via Wipro · Austin, TX · Cupertino, CA · Remote

  • Built custom LLM-powered code generation tooling and validated output quality against a baseline using similarity metrics, achieving ~30–40% improvement in generated code relevance.
  • Contributed to migrating a high-volume audit application (1M+ daily transactions) from Cassandra to MongoDB by rewriting queries for API changes, building new backend services, and validating data integrity between systems, reducing query latency from 10,000ms+ to under 1,000ms.
  • Built custom PyCharm and IntelliJ IDE extensions in Python and Java to automate repetitive developer setup and reduce boilerplate overhead across the team.
  • Configured Grafana and Splunk dashboards to monitor query performance and track bugs across backend services, supporting load testing and production observability.

Skills

Languages
  • Python
  • Java
  • JavaScript
  • TypeScript
Frameworks
  • Spring Boot
  • Maven
  • React
  • Angular
  • Hibernate
  • JUnit
  • FastAPI
Data & infrastructure
  • AWS
  • Docker
  • Kubernetes
  • MongoDB
  • Cassandra
  • MySQL
Observability & testing
  • Grafana
  • Splunk
  • Prometheus
  • JMeter
  • Postman
  • Git
AI
  • LLM integration
  • Agent orchestration
  • RAG
  • Model Context Protocol (MCP)
  • Claude Code
  • Google AI

Education

  • B.S., Software Engineering

    Western Governors University

    Expected 2027

  • A.S., Computer Programming and Information Systems

    College of the Sequoias · Visalia, CA

    2021

Languages
English (native), Mienh (conversational)
Outside work
3D printing, custom hardware design, home automation, travel, photography, sci-fi and fantasy literature

Contact

Hiring for backend or AI engineering? I'd love to hear about it.

jeffrey@jeffreysaelee.com
LinkedIn Résumé (PDF) Résumé (web)