Summary
Manuel Kelly is a computer engineer and research assistant in San Diego with eight years of hands-on experience building FPGA systems and applying machine learning to real-world problems. He has delivered flight-ready FPGA designs and high-speed optical communication modems (2.5G and 10G) for space applications, and has implemented end-to-end digital communication pipelines including LDPC/Viterbi FEC, ARQ, and Ethernet/IP transport. Currently pursuing ML research, Manuel works on diffusion-based offline reinforcement learning, fairness-aware multi-agent policies, and transformer-based sequential decision-making while co-authoring work on unlearning diffusion policies. His toolset spans VHDL/Verilog/SystemVerilog, AXI-based RTL, PyTorch/Flax, and embedded Zynq systems, enabling him to bridge FPGA hardware and ML software seamlessly. Notably, he combines space-grade engineering discipline with explorations in FPGA-accelerated ML and image upscaling—bringing production-ready rigor to cutting-edge research.
8 years of coding experience
6 years of employment as a software developer
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at San Diego State University
Cal Poly Pomona
Associate of Science - AS, Mathematics, Associate of Science - AS, Mathematics at Crafton Hills College