6 months ago
Cupertino, CA, USASenior
Responsibilities
- Develop and own SoC functional models from architecture through deployment, including infrastructure integration, testing, and debugging.
- Collaborate with architecture, RTL design, design verification, emulation, and software teams to align models and performance.
- Develop tooling and infrastructure that improves usability and effectiveness for internal and external partners.
- Optimize model and infrastructure performance for scalability across real-world AI workloads.
- Create well-documented, maintainable, and reusable software.
- Simulate the performance of current and upcoming state-of-the-art Transformer models on the ASIC architecture versus GPUs, TPUs, and other alternatives.
Requirements
- Bachelor’s degree or equivalent practical experience.
- 5 years of experience in software development involving data structures and algorithms.
- 5 years of experience developing and testing software models or simulations of shipping ASICs.
- 3 years of experience modeling SoC-relevant technologies such as DRAM, HBM, I2C, SPI, and PCIe.
- Expertise in functional modeling of ASICs, TPUs, GPUs, CPUs, or equivalent accelerators.
- Strong command of C++ and familiarity with Python for scripting and automation.
- Experience bridging simulation and analysis across physical link I/O, memory, chip firmware, system software, and overall performance.
- Preferred: Master’s or PhD in Computer Science or a related technical field.
- Preferred: Experience with computer architecture, SoC design, and RTL languages.
- Preferred: Ability to solve ambiguous problems and communicate effectively in writing and verbally.
About Etched
Etched designs and sells AI inference chips and servers that hard‑code support for specific model architectures. Its first ASIC, Sohu, targets transformer models to deliver high‑throughput, low‑latency inference for workloads such as real‑time generation. Founded in 2022 and headquartered in San Jose, California, the privately held company serves organizations building large‑scale AI inference clusters and infrastructure.