Deep Learning Performance Architect
Core
Develop highly optimized deep learning kernels and perform performance analysis, tuning, and architectural design for GPU-accelerated inference software.
Role type
Senior IC deep learning performance software engineer
Builds
GPU-accelerated inference software (Tensor-RT) for automotive, image understanding, and speech understanding applications
Domain
Deep learning, GPU computing, inference optimization
Deliverable
production ML models
Required skills
C/C++ programming, software design, performance modeling, profiling, debugging, code optimization, CPU/GPU architecture knowledge, CUDA or OpenCL programming
Preferred skills
Python experience, SW Agile skills
Technologies
CUDA, OpenCL, Tensor-RT
Responsibilities
Develop optimized deep learning kernels for inference, conduct performance optimization and tuning, collaborate with cross-functional teams on innovative solutions
Seniority
Senior, hands-on IC
