ML Accelerator Performance Tools Intern

Etched; San Jose (CA); On-site; USD 20,000 - 31,000; Full time

Job summary

Etched in San Jose is seeking a performance-focused intern to design and build tooling for our ML accelerator. You will collect data, develop traces, and help correlate CPU, accelerator, and memory events to identify bottlenecks and optimize workloads.

Work with hardware, software, and firmware teams to improve developer productivity and unlock full hardware potential for demanding ML applications.

Qualifications

• Strong programming skills in C++ or Rust; Python is a plus.
• Pursuing a bachelor’s degree in computer science or related field.
• Interest in low-level performance analysis, profiling, and optimization.
• Familiarity with performance analysis tools such as Nsight, VTune, Xprof, Perfetto.

Responsibilities

• Build components of the performance analysis and profiling infrastructure.
• Collect and analyze performance data from the ML accelerators, including counters and traces.
• Develop tooling to trace host-side runtime activity and accelerator execution.
• Correlate performance events across CPUs, accelerators, storage, networking, and workloads.
• Build analysis/visualization tools to identify bottlenecks and optimize models.
• Collaborate with hardware, firmware, compiler, and inference engineers to improve productivity.

Skills

C++

Rust

Python

Education

Pursuing CS degree

Tools

Nsight

VTune

Xprof

Perfetto

Job description

Etched in San Jose is seeking a performance-focused intern to design and build tooling for our ML accelerator. You will collect data, develop traces, and help correlate CPU, accelerator, and memory events to identify bottlenecks and optimize workloads.

Work with hardware, software, and firmware teams to improve developer productivity and unlock full hardware potential for demanding ML applications.