Staff Engineer - Post-Silicon Validation and Characterization

We are seeking an experienced to own the end-to-end testing, characterization, and failure analysis strategy for complex, next-generation multi-die packages.

You will own the complete Post Silicon validation lifecycle across a multi-die architecture—covering high-speed die-to-die (UCIe) interconnects, Power Delivery Networks (PDN/PMIC), Platform Management Controllers (PMC), PCIe/CXL subsystems.

Additionally, you will apply statistical analysis and machine learning to test data—driving outlier detection, bench-to-ATE correlation, and predictive telemetry signals—without treating ML models as a substitute for true physical root-cause analysis.

What you’ll do

Test content and automation

• Test Plan Ownership: Define development test strategies, coverage targets, content architecture, and strict traceability from architectural requirements to validation evidence.
• Bare-Metal & C/Python Test Content: Write low-level C and Python test suites—including bare-metal exercisers, traffic generators, stress patterns, and custom firmware drivers/hooks.
• Scalable Automation & HIL: Build robust test frameworks featuring instrument control, automated sequencing, structured result capture, and Hardware-in-the-Loop (HIL) CI/CD integration for continuous validation.
• Bench-to-ATE Handoff: Develop lab-to-ATE correlation test suites and drive smooth handoffs to Product & Test Engineering (PTE)
• Own the development test plan: coverage goals, content architecture, and the traceability between a requirement, the test that exercises it, and the evidence it passed.

Characterization and margin

• Injection Frameworks: Build minimally invasive fault-injection hardware/software infrastructure that perturbs target datapaths without destabilizing the test setup itself.
• Protocol & Platform Fault Testing: Execute rigorous error campaigns targeting CRC retries, lane degradation/repair, sideband timeouts, PCIe AER, DMA/IOMMU translation faults, and PMIC reset conditions.
• Firmware & Resilience Testing: Validate system firmware error handlers, watchdog timers, and hardware-level fault containment behavior under out-of-spec conditions.

Required qualifications

• Experience: 8–10+ years in Post-silicon validation, system software testing, silicon bring-up, or development test for complex SoCs / ASICs / GPUs.
• Software/Firmware Skills: Advanced proficiency in C and Python for low-level bare-metal test content, hardware abstraction, and automation frameworks.
• Silicon Characterization: Proven experience with Shmoo plotting PVT corner testing, jitter/margin analysis, and guard-band definition.
• Fault Injection Expertise: Hands-on experience building or executing error-injection and recovery validation campaigns on production silicon.
• Lab Instrumentation: Fluency with oscilloscopes, protocol analyzers (PCIe/CXL), logic analyzers, BERTs, thermal chambers, controllable power supplies, and JTAG debuggers.
• High-Speed & System Protocols: Practical, protocol-level understanding of high-speed serial interfaces (PCIe, CXL, or UCIe) and control buses (I2C, SPI, UART, PMBus, SMBus).
• Power Systems: Solid grasp of system power delivery—including sequencing, PMIC telemetry, DVFS, voltage regulation, and protection trip limits.
• Data & Tooling: Competency with toolchains (Git, CMake, GCC/Clang, CI pipelines) and statistics/data analysis over test populations.
• Education: BS or MS in Electrical Engineering, Computer Engineering, Computer Science, or equivalent practical experience.
• AI Tool usage : AI coding and automation tool is must for this role