ML ASIC Performance Modelling Intern (AI2360)

$43 - $45/Yr

SiMa Technologies - San Jose, CA

Part-time - Intern

San Jose, CA

Publishing Industries

About the position

As a member of the Platform Architecture team, you will be working on using your knowledge of computer architecture to model our Machine Learning Accelerator to perform coarse modeling of the power, performance and area of the MLA for different configurations of the MLA as well as for different ML workloads like LLMs and VLMs. We are looking for a dynamic computer architecture intern with a background in computer architectures for this position. We are looking for candidates who are about to complete their Master's or PhD or who have already completed their Master's or PhD. We are also open to a part-time or remote role starting now, with a possibility of converting to a full time internship in the summer.

Responsibilities

• Model the Machine Learning Accelerator (MLA) for power, performance, and area analysis.
• Perform coarse modeling for different configurations of the MLA.
• Analyze different ML workloads such as LLMs and VLMs.

Requirements

• Pursuing MS or PhD in Computer Architecture
• Thorough knowledge of coding with Python and C++

Nice-to-haves

• Strong understanding of machine learning architecture like systolic arrays.
• Can-do attitude; Curious, creative, and good at solving problems.
• Execution and results oriented; Self-driven; Thinks Big and is highly accountable.
• Good communication skills.

Benefits

• Hourly pay rate range of $43 - $45
• Possibility of converting to a full-time internship in the summer