Staff Kernel Optimization Engineer

Stack

Responsibilities

• ▹Develop design specifications for new machine learning and linear algebra kernels and map them to the Cerebras WSE system using parallel programming algorithms
• ▹Develop and debug a 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
• ▹Use mathematical models and analysis to measure software performance and inform design decisions
• ▹Develop and integrate unit and system testing methodologies to verify the functionality and performance of kernel libraries
• ▹Study emerging trends in machine learning applications and help evolve the kernel library architecture for the computational challenges of state-of-the-art neural networks
• ▹Interact with chip and system architects to optimize instruction sets, microarchitecture and IO of next-generation systems

Requirements

• ▹Bachelor's, Master's, PhD or foreign equivalents in Computer Science, Computer Engineering, Mathematics or related fields
• ▹Understanding of hardware architecture concepts and comfort learning the details of a new hardware architecture
• ▹Skilled in C++ and Python
• ▹Good knowledge of library and/or API development best practices
• ▹Strong debugging skills and knowledge of debugging complex software stacks

Nice to have

• ▹Experience in kernel development and/or testing
• ▹Familiarity with parallel algorithms and distributed memory systems
• ▹Experience in programming accelerators such as GPUs and FPGAs
• ▹Familiarity with machine learning neural networks and frameworks such as TensorFlow and PyTorch
• ▹Familiarity with HPC kernels and their optimization

Soft skills

About the company

Cerebras builds the world's largest AI chip, 56 times larger than GPUs, delivering training and inference over 10 times faster than GPU-based hyperscale cloud inference services. It works with leading model labs, global enterprises and AI-native startups; OpenAI announced a multi-year partnership with it.