Senior Deep Learning Performance Architect
Core
Design next-generation architectures to accelerate AI and high-performance computing applications by analyzing performance, cost, and power trade-offs.
Role type
Senior IC deep learning performance architect
Builds
Deep learning frameworks, libraries, compilers, and hardware/software architectures
Domain
AI computing, high-performance computing, GPU/ASIC architecture
Deliverable
production ML models
Required skills
GPU or Deep Learning ASIC architecture design, performance modeling, architecture simulation, profiling, machine learning fundamentals, Python, C, C++
Preferred skills
Deep neural network training/inference optimization, PyTorch, JAX, TensorRT, CUDNN, CUBLAS, CUTLASS, MLIR, Triton, CUDA, OpenCL, DL accelerator workload analysis
Responsibilities
Develop innovative architectures to extend deep learning performance and efficiency; Analyze performance, cost, and power trade-offs using analytical models and simulators; Understand interplay of hardware and software architectures on algorithms and programming models; Develop and analyze deep learning frameworks, libraries, and compilers; Collaborate with software, product, and research teams to guide deep learning HW and SW direction
Seniority
Senior, hands-on IC
