AI Inference
Performance Engineer
Building faster inference through latency benchmarks, runtime validation, and GPU-aware systems
CUDA • C++ • PyTorch • Model Serving • Latency Benchmarking • Runtime Systems
FEATURED WORK
SimLab
AI-powered platform that turns natural-language prompts into sandboxed, interactive physics simulations in real time.
Inference Runtime Regression Gate
CI validation gate that benchmarks baseline vs candidate inference runs and blocks meaningful p95 latency regressions before release.
Matching Engine
Deterministic C++ limit order book with price-time priority, partial fills, cancellations, and throughput benchmarking.
Lock-Free Ring Buffer
Lock-free SPSC ring buffer with tuned wait strategies and benchmarked throughput/latency performance.
Real-Time UAV Simulator
Real-time drone simulation with deterministic physics and stable control systems.
Performance Inspector
Real-time profiling tool for identifying runtime bottlenecks and performance regressions.
ScratchFX
GPU shader-based reveal system optimized for real-time rendering.
Static
A first-person psychological horror game built with dynamic rule-based gameplay systems.
Stuffed Animal Nightmares
A stylized stealth-horror prototype featuring AI-driven enemy behavior and player evasion mechanics.
FlagStorm
A multiplayer capture-the-flag prototype with networked gameplay systems and team-based objectives.
EXPERIENCE
Real-Time Simulation Systems at Boeing
- Built real-time simulation systems in Unity + C++ modeling aircraft electrical systems and faults
- Designed modular, state-driven architectures and optimized CPU, memory, and rendering performance
Infrastructure at Prisms VR
- Built TeamCity PR gates across 3 Unity repositories, blocking failed builds before merge.
- Automated package sync, lockfile regeneration, CI triage, and release validation workflows.