Machine Learning/Deep Learning/AI over Meta Training/Inference Accelerator (MTIA):

• Machine Learning (ML) Software Stack Production

• Machine Learning (ML) Compiler Optimizations

• ML Model Analysis, Performance Optimizations, and Launch

LLVM Compiler Engineering and Performance Engineering on mobile platforms (iOS/Android)

• performance, code size, startup delay, power consumption, etc.

• interactions with existing mobile apps and the mobile ecosystem

• Scaling and Parallelizing Applications across multi-core CPUs, multi-SP GPUs, and special accelerators utilizing OneAPI.

• LLVM/ICC Compiler Analysis and Performance Optimization:

Loop Optimizations (LoopOpt), Inter-procedural optimizations (IPO), Vectorization, etc.

• Intel Architecture (IA) Performance Leadership

• Parallel Programming and Application Acceleration across homogeneous and heterogeneous

architectures

• Path-finding Activities

Apple Machine Learning (ML) Software Stack Bring up:

• Software Engineer: Apple’s Big Data/Deep Learning Neural Engine (ANE)

• Performance Architect: Apple’s Big Data/Deep Learning Neural Engine (ANE)

LLVM Compiler Software Engineer

Intel Compiler Group (ICC)

Intel Corp.

Santa Clara, CA, USA, 95054

• Program Analysis, Compiler Engineering

• Performance Analysis and Optimizations of Large-scale applications

• Compiler Efficiency and Compile-time Improvements