Inference Software Engineer
EtchedCupertino, California, United States
Posted February 19, 2025
Full Time
About the Company
Etched specializes in developing cutting-edge servers by integrating transformer architecture directly into their chips. This innovative approach results in unparalleled processing power for transformer-based inference tasks. The company's core value proposition lies in its ability to deliver superior performance and efficiency, making it a leader in the AI hardware sector.
Job Description
Etched is building AI chips designed to handle complex models. They are seeking an Inference Software Engineer to contribute to the architecture and design of their Sohu host software stack. Responsibilities include implementing high-performance, modular code, interfacing with firmware/drivers, and collaborating with AI model researchers and product teams. The company focuses on hardware-accelerated AI and the concept of ASICs tailored for specific model architectures.
Requirements
- Experience with C++ and Python
- Familiarity with transformer model architectures and inference serving stacks (vLLM, SGLang, etc.) or experience working in distributed inference/training environments
- Experience working cross-functionally in large software and hardware organizations
Benefits
- Full medical, dental, and vision packages
- Housing subsidy
- Daily lunch and dinner
- Relocation support
