Hello! I'm Wilson, a Computer Science and Physics graduate from The University of Virginia, currently pursuing my Master's degree at Carnegie Mellon University. My experience spans developing AI-powered tools, building machine leaning models for real-world problems, and architecting cloud solutions. I'm passionate about the intersection of AI research and practical applications, with hands-on experience in ML infra, web development, game development, and data analytics.
Whether I'm architecting AI-based solutions, creating educational physics games, or exploring machine learning algorithms, I thrive on solving complex problems and translating innovative ideas into real-world solutions. I'm always eager to take on new challenges that push the boundaries of what's possible with technology.
Beyond academics, I've done a little bit of astrophotography, fully documented by the blog also in the Astro page. A dream of mine is to have one of my images be on apod.nasa.gov!
Learning SGLang
An illustrated guide to inference engines, from the problems up. One picture per chapter that you step through — attention, KV cache, batching, the scheduler, prefix caching — each chapter ending on the question the next one answers.
Timeline Drawer
A little tool for drawing concurrent timelines by hand — the kind you end up sketching when explaining scheduling, pipelining, or anything that overlaps in time. Built mostly because they look pretty.
Carnegie Mellon University
Master of Science in Artificial Intelligence and Innovation
Relevant Courses:
Computer Architecture, Compilers, Operating Systems, Cloud Computing, Machine Learning, Deep Learning, LLM Systems, AI Engineering, Generative AI for Music, NLP
The University of Virginia
Bachelor's Degree in Computer Science & Physics
Relevant Courses:
Data Structures & Algorithms, Software Development Methods, Computer Architecture, Machine Learning, Cybersecurity, Compilers, Operating System, Database Systems, Cloud Computing, Quantum Computing
Software Engineering Intern
- Engineered a virtual fault-injection framework in C++20 for security controllers, simulating instruction-skip attacks to uncover secure-boot bypass vulnerabilities
- Authored hardened security patches mitigating glitch attacks via compiler-aware anti-glitch loop checks and reinforced verification primitives
- Debugged bare-metal firmware and analyzed raw Arm disassembly to confirm both vulnerabilities and their fixes
- Extended existing test suites to exhaustively evaluate Secure Boot verification logic under fault-injection scenarios
Software Development Engineer Intern
Amazon Web Services
- Engineered Amazon Q-powered AI unit test generation tool, raising code coverage to up to 90% across services
- Integrated into Amazon's CI/CD pipeline, enabling automatic test generation and saving ~10 hr/wk of manual testing
- Designed event-driven, scalable architecture on AWS to support asynchronous test generation workflows
- Developed multi-stage validation pipeline to detect and filter LLM hallucinations, significantly improving test reliability by eliminating invalid test cases before integration
SGLang-Omni Contributor
June 2026 – Present
Open-source contributor to SGLang-Omni, primarily working on ASR model serving optimization.
NodeTorch – Visual ML Model Builder
Apr 2026 – Present
Educational drag-and-drop node-based environment that lets users compose neural networks visually and train them, giving users a sandbox to experiment with model architectures without writing code from scratch.
Designed a layered, registry-driven execution engine separating graph runtime, type system, and ML domain. Built rich interactive visualizations of every layer's behavior (forward activations, parameter distributions, attention patterns, loss surfaces). Integrated an in-app AI assistant with a backend agent loop allowing any LLM to interact with the app through a schema-defined tool interface.
AI-powered social platform using React Native and FastAPI, enabling users to create interactive audio content through conversations with an AI host. Architected end-to-end AI content pipeline: GPT-4o mini script generation, Whisper transcription, Gemini image generation and ElevenLabs TTS with word-level subtitle alignment.
Designed scalable backend with async PostgreSQL using psycopg3, deployed on GCP. Implemented semantic search with Qdrant and OpenAI embeddings for content discovery. Engineered secure infrastructure (JWT, rate limiting, moderation) and stress-tested with Locust simulating hundreds of concurrent users.
Developed a real-time computer vision-powered hand gesture recognition system with PyTorch and OpenCV, achieving 95% confidence for gesture classification across 12 distinct hand poses captured via webcam feed.
Built gesture-to-keyboard mapping application motivated by accessibility and hands-free computing needs.