
Software Engineer Intern — AI Systems Integration
OpenQQuantify
Cut LLM inference-to-schematic latency from 8s to 4.5s for complex engineering queries. Shipped a Python/FastAPI microservice that reduced memory footprint 22% via AI payload optimization, holding up under high user load. Built a Python/Godot/Omniverse Synthetic Data Engine generating 15,000+ validated sensor data points for industrial ML training.










