AI Software Engineer with experience in building high-performance AI inference systems and scalable cloud software. My work sits at the intersection of deep learning and systems engineering, with a strong focus on hardware-aware deployment and real-world performance optimization.
My current work focuses on the PyTorch ecosystem, along with hardware-aware inference, LLM serving, and MLOps automation.
I enjoy research and mathematics, and have published a few papers so far. I’m excited to continue growing in this space.
My academic background has shaped how I approach engineering: practical, efficiency-driven, and collaborative. I like turning complex AI ideas into reliable, production-ready systems that deliver measurable impact.