Guoteng Rao

I am a Senior Machine Learning Infrastructure Engineer with over a decade building large-scale distributed systems and production ML platforms, focused on training, deployment, monitoring, and optimization for high-throughput and autonomous driving environments. I have led and mentored engineering teams, delivered GPU/runtime optimizations, and implemented CI/CD and observability to improve system performance and accelerate research-to-production cycles.

My hands-on experience spans distributed training on Kubernetes, ML compiler/runtime integrations (ONNX Runtime, TensorRT), multi-petabyte data pipelines, and real-time model serving with Python and C++. I collaborate cross-functionally to align infrastructure with product goals, drive reliability at scale, and ship reproducible ML systems for demanding environments.