Etched
Design Verification Engineer - SoC
Austin · Staff+
Sponsorship not specifiedDetected 97 days ago
PythonData AnalysisNLPVerilogResearch
About the role
- You will ensure the custom IPs powering our chips - including systolic arrays, DMA engines, and NoCs - are robust, high-performance, and silicon-ready.
Responsibilities
- Work closely with architects and RTL designers on verifying the performance features of the design and correlating with performance models (both pre-silicon and post-silicon).
- Develop test plans and test infrastructure/tools for performance tuning, correlation, and verification.
- Improve and maintain the architectural performance models.
- Develop tests in SystemVerilog, Python, or vectors to debug and correlate the RTL and performance model.
- Develop SystemVerilog or Python-based checkers for verifying the performance features.
- Drive end-to-end performance tuning, ensuring optimal hardware utilization, software efficiency, and architectural alignment across the ASIC design lifecycle.
Requirements
- Strong understanding of digital design, RTL, and ASIC design flows.
- Hands-on experience with performance verification, simulation, and modeling.
- Familiarity with performance bottleneck analysis, compiler optimizations, and workload tuning
- You may be a good fit if you have
Benefits
- Medical, dental, and vision packages with generous premium coverage
- $500 per month credit for waiving medical benefits
- Various wellness benefits covering fitness, mental health, and more
- Develop coverage monitors and analyze coverage to ensure all performance features are covered.
- Comfortable developing checkers, coverage monitors, and testbenches in SystemVerilog.
Company info
- We are the first inference-focused frontier AI system, betting early on transformer and transformer-like architectures and on increasing model sizes.
- We are a fully in-person team in San Jose (Santana Row), and greatly value engineering skills.
This listing is sourced directly from Etched's careers page and normalized into a canonical job model.