Leading the ML Deployments area composed of Runtimes, Compilers and Solutions teams. Together we build high performance runtimes and APIs for ML inference, leverage, extend and build industry leading compiler technologies into SOTA Cruise compiler products, and deliver SOTA model optimizations all in service of accelerating ML inference wherever Cruise needs it most.

Leading the teams responsible for ML performance requirements for next generation hardware (ML Architecture), ML platform abstractions to support on vehicle ML execution (ML Runtime) and ML emulation of on vehicle results using cloud resources (ML Emulation).

Built complete hw / sw for two FPGA systems that made up Cruise's network accelerated camera ingest pipeline.

HDL Optimizations team with focus on Hardware-Software co-design

Supported customers in all areas of MathWork's Simulink, Communications, and Signal Processing based products

Teaching Assistant for Introduction to Digital Circuits.

As a Ph.D. research assistant in Professor Anupam Madhukar's Nanostructure Materials and Devices Laboratory, my work focused on the fabrication of quantum dots for single photon emission/detection using molecular beam epitaxy (MBE) on patterned substrates in the GaAs/AlAs/InAs materials systems. Techniques focused on the control of spatial positioning and size distribution of quantum dots. Experience with scanning electron microscope (SEM), atomic force microscope (AFM), E-beam lithography, photolithography, wet chemical etching of GaAs, Reflection High Energy Electron Diffraction (RHEED) and ultrahigh vacuum system operation and maintenance.

ASIC verification

ASIC verification and FPGA design.