“A hands-on Optimizer coming from GPGPU and going to Deep Learning”

Expertise in:
+ Deep Neural Network Training/Inference Optimization
+ Multithreaded programming and performance tuning/optimization (OpenMP, CUDA, OpenCL)
+ Heterogeneous-Multicore/Manycore architecture simulation
+ EDA algorithms/tool development, Low power RTL design, UVM based verification and FPGA prototyping