Education
University of Michigan
Ann Arbor, MIB.S.E. in Computer Science, summa cum laude
December 2025GPA: 3.80/4.00 | Dean's List: 2022–2025
Relevant Coursework:
NLP, Parallel Programming with GPUs (CUDA), Web Systems, Database Management, Computer Security, DSA
My Projects
Trajan
Real-time probabilistic analytics platform serving 300+ daily active users. Built full data pipeline, sportsbook-agnostic parlay scraper, and Monte Carlo ML models for odds analysis at 89% predictive accuracy.
Cyberwright
Static code analyzer for compile-time security vulnerability detection using AST traversal, custom rule sets, and pattern-matching across dependency graphs. Placed 1st of 72 teams at the Ross Business+Tech Innovation Jam.
Course Companion
An LLM-powered application integrating university APIs, Canvas LMS, and Google Calendar API, helping students plan and manage their schedules more efficiently.
Generative AI for Photonic Inverse Design
Research project developing deep learning models including tandem networks, VAEs, and GANs for thin-film optic inverse design. Top model surpassed prior state-of-the-art by 25% in accuracy.
MotionSurfer
An immersive gaming experience that uses computer vision motion tracking to map player movement to key presses, allowing full-body control instead of traditional touch input.
Fresco
AI-powered food management system that tracks expiration dates, provides optimal storage conditions, and suggests recipes to reduce food waste.
Academic Work
Insta485
Client-side dynamic Instagram clone using React, Flask, and SQLite with a REST API backend and Jinja templating.
MapReduce
High-performance multi-process, multi-threaded MapReduce server for distributed data processing on a single machine.
Search485
Scalable search engine with web scraping, inverted index, and TF-IDF ranking across crawled web content.
Research Experience
Generative AI for Photonic Inverse Design
September 2023 – May 2024
- Benchmarked deep learning models (tandem networks, VAEs, GANs) for thin-film optic inverse design across 500+ TMM-generated datasets
- Top model surpassed prior state-of-the-art by 25% in accuracy, improving predictive robustness by 30%
- Worked with PhD supervisor to apply ML to thin-film optic inverse design for photovoltaic applications
Related publication: DOI: 10.29026/oes.2022.210012
Work Experience
Lead Software Engineer
RemoteTrajan
June 2025 – Present- Architected real-time probabilistic analytics platform serving 300+ daily active users, processing 10M+ API calls/month across 20+ data sources with sub-100ms query latency via WebSocket and Redis pub/sub
- Designed Redis-backed rate-limiting middleware enforcing per-user throttling, reducing database load by 40% under peak traffic
- Built NumPy-vectorized Monte Carlo simulation engine running 10,000+ iterations per bet evaluation at 89% predictive accuracy against live market close prices
- Developed LangChain + OpenAI API assistant with custom MCP tool-calling across 50,000+ historical data patterns for natural-language risk analytics
Software Engineering Intern – Perception
Austin, TXTerraFirma Inc.
May 2025 – August 2025- Owned full perception stack as employee #5; integrated Zed X One 4K cameras on Nvidia Jetson Orin AGX for stable real-time robotics video streaming
- Optimized GStreamer pipeline with H.265 + adaptive bitrate, achieving sub-200ms glass-to-glass latency for non-line-of-sight teleoperation
- Reduced view-mode switching from 10s to 20ms via dynamic GST compositor pad resizing with LiDAR integration; ~99% reduction in video artifacts
Software Engineering Intern
Ann Arbor, MIUniversity of Michigan CAEN
January 2025 – December 2025- Built ML compliance pipeline achieving 92% accuracy in regulatory issue detection at sub-250ms via OpenAI API and LangChain
- Managed AWS infrastructure (IAM, Lambda, S3) handling 30+ proposals/day at 300ms average latency
- Architected microservices backend with Docker, FAISS, PostgreSQL; improved throughput 30%, zero downtime across 50+ concurrent users
Project Lead – ML Flight Price Prediction
Ann Arbor, MIMichigan Data Science Team
January 2025 – May 2025- Led 20+ member team using gradient boosting + time-series feature engineering to 85% accuracy
- Built Streamlit web app for real-time price forecasts across 1,000+ city-pair markets
Machine Learning Engineer – Poker AI
Ann Arbor, MIMichigan Data Science Team
September 2023 – September 2024- Developed DQN and Deep Monte Carlo agent trained on 50,000+ hands from CMU's Pluribus agent
- Reduced action-selection latency 20%; 40% win rate increase against baseline AI over 10,000 simulated games
Project Lead & ML/CV Engineer
Ann Arbor, MIMHacks
November 2023- Led team of 4 building MotionSurfer: computer vision motion-tracking game using OpenCV, CVZone, Mediapipe