onsite
Senior SoC EMIR Engineer - Cloud Scale Machine Learning - Amazon Web Services
ML Engineer
Senior engineer responsible for EMIR sign‑off of high‑performance ML SoCs, defining power‑grid best practices, creating demand‑current models, and collaborating with architecture, verification, and physical design teams.
About the role
Key Responsibilities
- Lead EMIR (Electrical, Mechanical, Interface, Reliability) sign‑off activities for Inferentia and Trainium SoCs, ensuring compliance with AWS quality standards.
- Define and propagate best‑practice methodologies for power grid design and power‑integrity analysis across multiple product generations.
- Develop and maintain test cases, stimulus vectors, and simulation environments to accurately model demand currents and validate power delivery networks.
- Collaborate closely with architects, designers, verification engineers, power‑integrity specialists, and physical design teams to resolve cross‑domain issues.
- Drive root‑cause analysis of EMIR failures, propose corrective actions, and document lessons learned for future projects.
Requirements
- 5+ years of experience in SoC hardware engineering with a focus on EMIR, power‑grid design, or reliability.
- Strong knowledge of power‑integrity concepts, IR‑drop analysis, and signal‑integrity verification.
- Proficiency in hardware description languages (e.g., Verilog/SystemVerilog) and scripting languages such as Python for test automation.
- Demonstrated ability to work with cross‑functional teams in a fast‑paced, large‑scale environment.
- Excellent problem‑solving and communication skills, with a track record of delivering high‑quality hardware at scale.