Deep Learning Performance Software Engineer
Core
Develop compilers, DSLs, and highly optimized deep learning kernels for GPU-accelerated workloads.
Role type
Senior IC deep learning performance software engineer
Builds
GPU-accelerated deep learning software and compiler architectures
Domain
AI hardware acceleration and compiler infrastructure
Deliverable
production ML models
Required skills
C/C++ programming, compiler architecture design, DSL development, performance analysis, XLA, TVM, MLIR, LLVM, deep learning models and algorithms
Preferred skills
none stated
Technologies
XLA, TVM, MLIR, LLVM
Responsibilities
Develop compilers and DSLs for deep learning workloads; Design and implement highly optimized deep learning kernels; Continuously improve the compiler architecture for current and next generation chips; Perform performance analysis on emerging AI workloads and integrate with AI frameworks
Seniority
Senior, hands-on IC
