Manager kernel software
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
Manager, kernel software engineer (AI/HPC)
Builds
High-performance kernel library of parallel and distributed algorithms for training and inference on Cerebras WSE System
Domain
AI hardware acceleration / High-Performance Computing (HPC)
Deliverable
production ML models
Required skills
C++, Python, low-level systems programming, hardware architecture concepts, performance optimization, debugging complex software stacks, leading technical teams, mentoring engineers, setting technical direction
Preferred skills
leading teams in kernel development, parallel algorithms, distributed memory systems, accelerator experience (GPUs, FPGAs), machine learning frameworks (TensorFlow, PyTorch), HPC kernel strategies
Technologies
Cerebras WSE System, CSL (C-like domain specific language), assembly, TensorFlow, PyTorch
Responsibilities
Develop design specifications for new machine learning and linear algebra kernels; Develop and debug kernel library of highly optimized low level assembly instruction and C-like domain specific language routines; Develop and debug high-performance kernel routines in low-level assembly and a custom C-like (CSL) language; Using mathematical models and analysis to measure the software performance and inform design decisions; Develop and integrate unit and system testing methodologies to verify correct functionality and performance of kernel libraries; Study emerging trends in Machine Learning applications and help evolve Kernel library architecture; Interact with chip and system architects to optimize instruction sets, microarchitecture, and IO of next generation systems
Seniority
Manager, hands-on IC with team leadership
