Lead Diagnostics Software Engineer, ATE Integration
HybridMarkham, Ontario, Canada
Job Summary
Lead post-silicon SLT and functional GFX IP feature diagnostics onto wafer sort and ATE hardware configurations by defining technical roadmaps and deployment strategies. Architect software utilities to convert diagnostic sequences and compute workloads into cycle-accurate vector formats compatible with high-end ATE testers. Serve as the primary liaison between GFX/Compute Diagnostics, Product/Test Engineering, and DFT teams to analyze platform dependencies and build deterministic models that emulate host behaviors. Optimize tester execution times while maximizing structural and functional test coverage for data center GPU IPs, including HBM controllers and matrix math engines. This role supports AMD's mission to accelerate next-generation computing experiences across AI, data centers, and embedded systems.
Required Qualifications
- 8+ years of experience in silicon engineering spanning post-silicon validation, product engineering, diagnostics development, or structural/functional test generation
- Strong programming background in C/C++ and Python, with a concrete understanding of bare-metal or driver-level programming, registers, firmware interactions, and system memory maps
- Proven hands-on experience with production-grade Automated Test Equipment platforms (e.g., V93000, UltraFLEX) and structural/functional testing at the wafer sort or final test level
- Expert understanding of structural pattern generation, vector timing, clock domains, and diagnostic patterns (such as functional vectors, BIST/MBIST, or scan compression output)
- Deep understanding of GFX and compute architectures, with proven ability to design and implement diagnostic and test cases that maximize coverage and proactively identify silicon issues early
- Bachelor's, Master's, or Ph.D. in Electrical Engineering, Computer Engineering, Computer Science, or a related technical field
Desired Qualifications
- Familiarity with high-volume manufacturing challenges unique to data center architectures, including high-power profiles, HBM integration, and multi-die chiplet interconnect protocols (e.g., UCIe, proprietary fabrics)
- Understanding of AI/ML principles and some experience in applying LLM & ML models in applications
- Experience with working in DevOps environment like GitHub, CI/CD pipelines
- Excellent problem-solving abilities with a keen eye for detail
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.