Performance Tools Intern
EtchedVisit Etched website
Etched is an AI-hardware company building rack-scale frontier inference clusters.
San Jose, United States
Funding history
About Etched
Etched co-designs chips, racks, software, and manufacturing systems for efficient inference of frontier AI models, targeting throughput, latency, cost, and power efficiency across prefill and decode workloads.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will build performance-analysis and profiling infrastructure. You will collect and analyze accelerator data, trace runtime and system activity, correlate events across distributed systems, create analysis and visualization tools, and help engineers identify and optimize performance bottlenecks.
Requirements
- Programming skills in C++ or Rust
- Understanding of computer architecture, memory hierarchies, and parallel programming
- Experience or strong interest in performance analysis, profiling, and optimization
- Experience or strong interest in operating systems, compilers, firmware, drivers, or low-level systems software
Responsibilities
- Build performance-analysis and profiling infrastructure
- Collect and analyze performance data from ML accelerators
- Develop tooling to trace runtime activity, system behavior, and accelerator execution
- Correlate performance events across CPUs, accelerators, storage, networking, and distributed workloads
- Build analysis and visualization tools for performance bottlenecks
- Work with hardware, compiler, firmware, and inference engineers on performance tools