Inference Architecture Intern: AI Accelerator Design

Etched; San Jose, Northern (CA, KY); Hybrid; USD 13,225,000 - 19,837,000; Full time

Benefits offered by this job

Housing support

Lunch & dinner

Mentorship

In-person office

Job summary

Etched in San Jose, CA is seeking Fall '26, Spring '27, and Summer '27 internships in Inference Architecture to contribute to next-generation AI accelerators. You will work on compute architectures and performance modeling for inference workloads, under mentorship from veteran engineers.

Join a hands-on, in-person team focused on cutting-edge hardware-software co-design, optimizing runtimes, and scaling multi-node inference. This internship offers housing support and daily meals in our office.

Qualifications

• Progress towards a Bachelor’s, Master’s, or PhD degree in computer science, computer engineering, applied mathematics, or a related field
• Proficiency in Python, C++
• Understanding of performance-sensitive or complex distributed software systems
• Ported applications to non-standard accelerator hardware or hardware platforms
• Deep knowledge of transformer model architectures and/or inference serving stacks

Responsibilities

• Support porting state-of-the-art models to our architecture and build testing capabilities
• Assist in building, enhancing, and scaling our runtime for multi-node inference
• Contribute to optimizing routing and communication layers
• Utilize performance profiling to identify bottlenecks and correctness issues
• Co-design HW instructions and model operations to maximize performance
• Implement high-performance software components for the Model Toolkit

Skills

Python

C++

Transformer models

Distributed systems

Linux

Education

Bachelor/Master/PhD progress in CS/CE/Math

Job description

Etched in San Jose, CA is seeking Fall '26, Spring '27, and Summer '27 internships in Inference Architecture to contribute to next-generation AI accelerators. You will work on compute architectures and performance modeling for inference workloads, under mentorship from veteran engineers.

Join a hands-on, in-person team focused on cutting-edge hardware-software co-design, optimizing runtimes, and scaling multi-node inference. This internship offers housing support and daily meals in our office.