Staff AI Application Engineer
Core
Build the model enablement platform and agent harness for partitioning, compiling, running, and profiling AI models across heterogeneous hardware (CPU, GPU, NPU, FPGA) to optimize end-to-end performance.
Role type
Staff AI Application Engineer (Systems/Compilers)
Builds
Model enablement platform, agent harness, and verification frameworks for the Metis and Europa AI platforms.
Domain
AI Infrastructure / Heterogeneous Computing / Systems Programming
Deliverable
production ML models
Required skills
System-level design, heterogeneous computing (CPU/GPU/DSP/NPU/FPGA), computer architecture, parallel programming, ML graph representations (PyTorch/ONNX), C++, Python, AI coding agents
Preferred skills
MLIR/TVM/XLA/TorchInductor/IREE, inference runtimes (ONNX Runtime), GPU compute (CUDA/OpenCL/Vulkan), large-model execution techniques (offloading/expert caching), agent environments/verification frameworks
Technologies
PyTorch, ONNX, MLIR, TVM, XLA, TorchInductor, IREE, CUDA, OpenCL, Vulkan, C++, Python
Responsibilities
Build reusable tools for model partitioning, compilation, and profiling; manage model ingestion and placement across AIPU matrix and RISC-V units; optimize heterogeneous execution for large models and multi-model pipelines; profile device/host time and data movement to maximize pipeline speedup; study critical customer models to drive platform improvements.
Seniority
Staff, hands-on IC with architectural ownership
