Senior Deep Learning Compiler Engineer
Core
Building the Deep Learning Compiler (DLC) to deliver leading inference performance, fast build time, and reduced memory footprints for GPUs acting as the brains of computers, robots, and self-driving cars.
Role type
Senior Deep Learning Compiler Engineer
Builds
Ahead-of-Time and Just-in-Time compilers for deep learning inference across data centers, personal devices, automotive, and robotics.
Domain
AI / Deep Learning / Compiler Infrastructure / GPU Computing
Deliverable
production ML models
Required skills
C/C++ programming, Python programming, compiler optimization algorithms, performance analysis, software design, debugging, test design
Preferred skills
CPU and/or GPU architecture knowledge, CUDA or OpenCL programming, experience with constrained resources/embedded platforms, MLIR, XLA, TVM, LLVM, PyTorch, GPU kernel generation
Technologies
CUDA, OpenCL, MLIR, XLA, TVM, LLVM, PyTorch
Responsibilities
Analyzing deep learning networks, developing compiler optimization algorithms, collaborating with deep learning software framework and hardware architecture teams, defining public APIs, crafting compiler infrastructure techniques for neural networks
Seniority
Senior, hands-on IC
