The role involves developing and maintaining functional performance models for hardware, building tools for correlation debugging and testing, collaborating with various cross-functional teams, and optimizing performance through architectural decisions, particularly leveraging GPUs.

Design and implement compilers tailored for proprietary hardware, focusing on mid-end and backend development, while providing insights on hardware architecture.

The Hardware System Engineer will design AI compute boards, collaborate across teams, debug hardware issues, and deliver effective silicon products.

The role involves training and optimizing large language models for MatX's hardware, setting up distributed systems for training and inference, and advising on hardware architecture.

The role involves silicon verification, including creating testbenches, driving verification plans, and ensuring silicon accuracy through advanced methodologies.

The ML Performance Engineer develops performance models, writes production libraries for ML, and collaborates on solutions from model to hardware.

The role involves developing scalable silicon physical designs, coordinating with multiple teams, and ensuring performance, power, and area results from RTL to GDSII.

The role involves implementing DFT for silicon products, integrating DFT solutions, and collaborating with design teams to optimize performance and functionality.

Design and optimize software kernels for specialized hardware, collaborating with ML Research and Hardware Engineering teams to integrate software stacks.

The Architect will deliver silicon architecture for AI models, producing specifications, working closely with teams for effective implementation, and analyzing performance.