Performance Modeling Engineer

Etched was founded on the belief that new hardware will be needed to run human- and superhuman-level artificial intelligence. Our ASIC systems deliver orders of magnitude higher performance than conventional AI chips. Etched is actively developing [Sohu](https://www.etched.com/), an ASIC exclusively for transformers, which will enable products that would be impossible with GPUs, like [real-time video generation models](https://twitter.com/Etched/status/1852089772329869436) and extremely deep chain-of-thought reasoning. And we're bringing this technology to market in months, not years. Sohu is hard-coded for individual model architectures and only supports transformers, but has an order of magnitude more throughput and lower latency than a B200. **WHAT YOU’LL DO** - **Develop and own SoC functional models** from architecture to deployment, including integration with infrastructure, thorough testing, and debugging. - Collaborate closely with **architecture, RTL design, design verification, emulation, and software teams** to ensure alignment and performance. - **Innovate tooling and infrastructure** to enhance usability and effectiveness for internal and external partners. - Optimize model and infrastructure performance, ensuring scalability for real-world AI workloads. - Create software that is **well-documented, maintainable, and reusable**, ensuring longevity and ease of future development. - Simulate performance of existing and upcoming state-of-the-art (SOTA) Transformer models on our ASIC architecture vs other alternatives (GPUs, TPUs etc) **WE’RE LOOKING FOR ENGINEERS WITH:** - Expert knowledge in **functional modeling** of ASICs (TPUs, GPUs, CPUs, or equiv. accelerators) - Strong command of C++ for modeling with Python familiarity for scripting and automation. - Insights bridging simulation to analysis of complex systems involving multiple domains (e.g., physical link IO / memory / chip firmware / system software / overall performance). - High interest in learning transformer architecture, developing insight into AI hardware/software co-design. - Passion for AI and a desire to push performance and efficiency boundaries. **Machine learning experience is not required.** This role will provide opportunities to ramp on relevant ML concepts on the job. Minimum qualifications: - Bachelor's degree or equivalent practical experience. - 5 years of experience in software development with data structures/algorithms. - 5 years of experience developing and testing software models/simulations of shipping ASICs. - 3 years of experience modeling SoC relevant technologies (DRAM, HBM, I2C, SPI, PCIe, etc.). Preferred qualifications: - Master’s or PhD degree Computer Science, or a related technical field. - Experience in computer architecture, SoC design, and RTL languages. - Experience solving ambiguous problems. - Excellent verbal and written communication skills. **If you're a talented software engineer who's excited to shape the future of AI, we encourage you to apply!** **To Apply:** Please visit our website at [](https://www.etched.com/careers) to submit your resume and cover letter. **Location:** Cupertino, California