Head of Software Architecture

Role Overview: As a Manager, Kernel Software at Cerebras Systems, you will lead a team of engineers in developing high-performance solutions for cutting-edge AI and HPC workloads. You will collaborate with industry and academia leaders to design software that fully utilizes the capabilities of the custom, massively parallel processor architecture. Your role will involve guiding the technical roadmap, overseeing the design and optimization of deep learning operations, and ensuring the delivery of robust, high-performing kernel libraries. Your leadership will directly impact the scalability of training workloads and drive breakthroughs in performance and efficiency. Key Responsibilities: - Lead the design and development of high-performance ML and linear algebra kernels for the Cerebras WSE using parallel programming techniques. - Guide a team in building optimized low-level routines in assembly and a domain-specific C-like language. - Utilize performance modeling to make informed design and optimization decisions. - Drive test development to ensure the correctness and performance of kernel libraries. - Evolve kernel architecture to support emerging ML models and workloads. Qualifications Required: - Bachelor's, Master's, PhD, or foreign equivalent in Computer Science, Computer Engineering, Mathematics, or a related field. - Proven experience in leading technical teams, including mentoring engineers, setting technical direction, and driving execution. - Proficiency in C++ and Python with experience in low-level systems programming. - Familiarity with library/API development best practices and performance optimization. - Excellent debugging skills across complex, layered software stacks. - Experience leading teams in kernel development, performance optimization, or low-level systems programming. - Hands-on experience with accelerators such as GPUs, FPGAs, or other custom hardware. - Familiarity with machine learning workloads and frameworks like TensorFlow and PyTorch. Company Additional Details: Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs, offering industry-leading training and inference speeds. The groundbreaking wafer-scale architecture enables the fastest Generative AI inference solution globally, transforming the user experience of AI applications. Cerebras serves top model labs, global enterprises, and cutting-edge AI-native startups, providing a work environment that empowers individuals to excel in groundbreaking advancements in AI. Role Overview: As a Manager, Kernel Software at Cerebras Systems, you will lead a team of engineers in developing high-performance solutions for cutting-edge AI and HPC workloads. You will collaborate with industry and academia leaders to design software that fully utilizes the capabilities of the custom, massively parallel processor architecture. Your role will involve guiding the technical roadmap, overseeing the design and optimization of deep learning operations, and ensuring the delivery of robust, high-performing kernel libraries. Your leadership will directly impact the scalability of training workloads and drive breakthroughs in performance and efficiency. Key Responsibilities: - Lead the design and development of high-performance ML and linear algebra kernels for the Cerebras WSE using parallel programming techniques. - Guide a team in building optimized low-level routines in assembly and a domain-specific C-like language. - Utilize performance modeling to make informed design and optimization decisions. - Drive test development to ensure the correctness and performance of kernel libraries. - Evolve kernel architecture to support emerging ML models and workloads. Qualifications Required: - Bachelor's, Master's, PhD, or foreign equivalent in Computer Science, Computer Engineering, Mathematics, or a related field. - Proven experience in leading technical teams, including mentoring engineers, setting technical direction, and driving execution. - Proficiency in C++ and Python with experience in low-level systems programming. - Familiarity with library/API development best practices and performance optimization. - Excellent debugging skills across complex, layered software stacks. - Experience leading teams in kernel development, performance optimization, or low-level systems programming. - Hands-on experience with accelerators such as GPUs, FPGAs, or other custom hardware. - Familiarity with machine learning workloads and frameworks like TensorFlow and PyTorch. Company Additional Details: Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs, offering industry-leading training and inference speeds. The groundbreaking wafer-scale architecture enables the fastest Generative AI inference solution globally, transforming the user experience of AI applications. Cerebras serves top model labs, global enterprises, and cutting-edge AI-native startups, providing a work environment that empowers individuals to exce