Senior AI Compiler Engineer, Algorithms and Code-Generation
Core
Designing and optimizing compilers for deep learning and AI workloads to enable high-performance inference on NVIDIA GPUs across data centers, personal devices, automotive, and robotics.
Role type
Senior IC AI compiler engineer (algorithms and code-generation)
Builds
High-performance AI inference engines and compiler toolchains (Ahead-of-Time and Just-in-Time)
Domain
AI/Deep Learning + Compiler Technology
Deliverable
production ML models
Required skills
CUDA programming, compiler optimization algorithms, C/C++, Python, performance analysis, debugging, API design
Preferred skills
GPU architecture knowledge (Hopper/Blackwell), deep learning frameworks (PyTorch/JAX), GPU kernel authoring, Nsight Compute, hardware bring-up
Technologies
CUDA, MLIR, LLVM, XLA, Triton, Nsight Compute, PyTorch, JAX
Responsibilities
Analyze deep learning networks and develop compiler optimization algorithms; define public APIs and implement compiler techniques for AI workloads; analyze and debug performance bottlenecks on GPUs
Seniority
Senior, hands-on IC
