Kernel Engineer
Core
Develop high-performance software solutions at the intersection of hardware and software, implementing and optimizing deep learning operations for custom, massively parallel processor architecture.
Role type
Senior IC kernel engineer (AI/HPC)
Builds
High-performance kernel library of parallel and distributed algorithms for training efficiency
Domain
AI hardware acceleration / High-Performance Computing (HPC)
Deliverable
production ML models
Required skills
C++, Python, hardware architecture concepts, low-level assembly programming, custom C-like domain specific language (CSL), debugging complex software stack, library and API development best practices
Preferred skills
kernel development and testing, parallel algorithms and distributed memory systems, programming accelerators (GPUs/FPGAs), Machine Learning neural networks (TensorFlow/PyTorch), HPC kernels optimization
Technologies
Cerebras WSE System, TensorFlow, PyTorch
Responsibilities
Develop design specifications for new machine learning and linear algebra kernels mapping to Cerebras WSE System; Develop and debug kernel library routines in low-level assembly and CSL language; Use mathematical models to measure software performance and inform design decisions; Develop and integrate unit and system testing methodologies; Study emerging trends in Machine Learning applications to evolve Kernel library architecture; Interact with chip and system architects to optimize instruction sets and microarchitecture
Seniority
Senior, hands-on IC
