Document retrieval
High-performance document retrieval and RAG — knowledge bases at six-figure file counts with strong accuracy targets (e.g. 107K+ files, 98%+ accuracy in production).
About
As a Machine Learning Engineer at Apple and Master’s student at Georgia Institute of Technology, I architect and deploy production-scale AI systems that drive meaningful business impact and enhance customer experiences. With over 2 years of experience shipping ML solutions that have generated ~$80M in annual revenue, I specialize in building sophisticated generative AI systems, large language model architectures, and retrieval-augmented generation (RAG) pipelines designed to serve millions of customers.
My expertise spans the full ML lifecycle — from designing high-performance document retrieval systems managing 100K+ files with over 98% accuracy, to building comprehensive evaluation frameworks with distributed LLM-as-judge infrastructure processing tens of millions of evaluations. I excel at transforming complex AI challenges into scalable, production-ready solutions through advanced prompt engineering, multi-model orchestration, and robust safety frameworks.
Beyond technical execution, I’m passionate about building teams and sharing knowledge. I actively mentor junior engineers, conduct technical interviews to strengthen our organization’s capabilities, and develop internal tooling platforms that accelerate innovation across teams. My graduate studies at Georgia Tech complement my applied work, allowing me to bridge cutting-edge research with practical engineering solutions.
I thrive at the intersection of academic rigor and industrial-scale deployment, turning state-of-the-art LLM technologies into reliable, impactful systems that solve real-world problems at scale.
High-performance document retrieval and RAG — knowledge bases at six-figure file counts with strong accuracy targets (e.g. 107K+ files, 98%+ accuracy in production).
Interfaces and internal tooling — prompt workflows, evaluation dashboards, and platforms teams use to ship generative AI safely.
End-to-end systems — orchestration, distributed LLM-as-judge evaluation at scale, safety layers, and observability for production LLMs.
Sunnyvale, CA · Hybrid
Cupertino, CA · Hybrid
Santa Clara, CA
Santa Clara, CA
Pleasanton, CA
Dublin, CA
Dublin, CA
Fremont, CA
M.S. Computer Science — Artificial Intelligence
Georgia Institute of Technology · GPA 4.0
B.S. Computer Science
University of Illinois Springfield · Summa Cum Laude · 3.91 GPA
Computer Science (transferred)
San Jose State University · Dean’s Scholar
Coding Instructor · CoderDojo
Taught students of all ages Scratch, HTML, CSS, and Java until they could build their own websites and apps for their portfolios.
Robotics Instructor · Imagineering
Taught middle school students the fundamentals of robotics, and designed and built the sensor-equipped demo robots used in the lessons.
| Certification | Issuer | Issued |
|---|---|---|
| Exploratory Data Analysis for Machine LearningCHSFEJUG46U5 | IBM | Apr 2024 |
| JenkinsUC-01c10c09-be6d-407c-b86c-5968124b50ed | Udemy | Aug 2023 |
| SwiftUI for iOS 14DC-1614301332633 | DesignCode | Feb 2021 |
| Flutter for DesignersDC-1614225860922 | DesignCode | Feb 2021 |
| The Complete 2020 Flutter Development Bootcamp with DartUC-f9d89e0b-f318-4f99-9b6f-bb1771a91b84 | Udemy | Jul 2020 |
| ROP Certificate | Contra Costa County | May 2020 |
Organization logos by Logo.dev.