Kernel Engineer

Cerebras Systems, a pioneering company in AI hardware, is seeking a Kernel Engineer to join their team in Bengaluru, India. The company builds the world's largest AI chip, which is 56 times larger than traditional GPUs, revolutionizing AI compute capabilities.

As a Kernel Engineer, you'll work at the fascinating intersection of hardware and software, developing state-of-the-art solutions for emerging problems in AI and HPC. You'll be part of a team responsible for designing, implementing, validating, and performance-tuning deep learning operations on highly parallel custom processors.

The role involves developing sophisticated parallel and distributed algorithms to maximize hardware utilization and accelerate neural network training to unprecedented speeds. You'll work with low-level assembly instructions and C-like domain-specific language routines, while also collaborating with chip and system architects to optimize next-generation systems.

The ideal candidate should have a strong academic background in Computer Science, Computer Engineering, or Mathematics, with expertise in C++ and Python programming. Knowledge of hardware architecture, debugging complex software stacks, and API development best practices is essential. Experience with kernel development, parallel algorithms, GPU programming, and machine learning frameworks would be highly advantageous.

Cerebras offers a unique opportunity to work on groundbreaking AI technology, with the chance to publish research and contribute to one of the world's fastest AI supercomputers. The company combines the stability of an established organization with the dynamic environment of a startup, fostering a non-corporate culture that respects individual beliefs and promotes continuous learning and growth.