Fei Kou is a Member of Technical Staff in the San Francisco Bay Area with eight years of engineering experience spanning low-latency finance systems to large-scale ML model optimization. After building high-throughput auto-quoting infrastructure at JPMorgan and improving firm-wide reference data at Nomura, Fei spent eight years at Facebook enabling and optimizing Llama inference—co-authoring work on efficient speculative decoding at scale. Now at Anthropic, Fei applies a blend of systems engineering and ML deployment expertise to productionize cutting-edge models. Comfortable across C++/Python performance work and distributed system design, Fei has a track record of turning research ideas into deployable, production-ready systems. A Stony Brook CS graduate, Fei brings a pragmatic, metrics-driven approach and a knack for squeezing latency and cost out of complex pipelines. Notably, Fei’s background bridges financial-grade reliability with research-forward ML inference optimizations.
8 years of coding experience
13 years of employment as a software developer
Bachelor of Science (BS) Computer Science, Bachelor of Science (BS) Computer Science at Stony Brook University
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
Contributions:6 pushes, 1 branch in 1 day
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.