Description
Job Summary
As a Debug Validation Engineer at Graphcore, you will drive post-silicon debug and validation activities for next-generation AI compute silicon and systems. Reporting to the Senior Director of Post Silicon Validation, you will lead teams focused on identifying, reproducing, analyzing, and resolving complex silicon, firmware, and system-level issues.
The Team
The Post-Silicon Debug and Validation team at Graphcore manages bring-up, fault diagnosis, and validation of Graphcore silicon and systems. The team works throughout the product lifecycle, from initial silicon bring-up to production readiness, collaborating closely with hardware, firmware, software, and systems teams.
Responsibilities and Duties
- Lead post-silicon debugging and validation efforts for AI compute silicon and platform technologies.
- Contribute to debug and validation activities across multiple projects.
- Analyze and address complex silicon, firmware, software, and system-level problems during bring-up and validation.
- Develop structured debug methodologies and failure analysis processes.
- Collaborate with architecture, RTL, firmware, software, and systems engineering groups to determine root causes and implement corrective measures.
- Drive debug of CPU, memory, interconnect, and high-speed I/O subsystems.
- Develop and improve automated debug, regression, and validation infrastructure using Python.
- Analyze logs, traces, telemetry, and hardware data to isolate and characterize system failures and performance issues.
- Support development of validation tests, debug tooling, and custom diagnostics.
- Define validation metrics, debug workflows, and reporting standards.
- Communicate technical risks, status, and recommendations to engineering leadership and cross-functional collaborators.
- Support silicon readiness reviews and contribute to product quality and release decisions.
- Contribute to continuous improvement of debug methodologies, validation infrastructure, and engineering workflows.
Candidate Profile
Essential:
- Experience in bare metal environments.
- Understanding of SoC and platform architectures.
- Expertise in debug infrastructure and post-silicon debug methodologies.
- Strong programming skills in Python, C, or debug scripting languages.
- Motivated self-starter with a collaborative approach.
- Experience in post-silicon validation in digital ASIC environments.
- Strong Linux and Python experience.
- Outstanding communication and collaboration skills.
- Excellent problem-solving, analytical, and diagnostic skills.
- Knowledge of scan, DFT, JTAG, and trace infrastructure.
- Strong debug skills including fault tree analysis and system-level debug techniques.
- Capability to operate autonomously on complex debug and validation tasks.
Desirable:
- Understanding of DFT flows.
- Experience developing tooling for parsing and analyzing debug data.
- Driver-level experience with technologies like PCIe, Ethernet, and Memory technologies.
- Experience using CoreSight and similar debug infrastructure.
- Understanding of mixed-signal components.
- Experience with Arm CPU architectures and system IP.
- Experience with AMBA protocols.
- Understanding of ML applications and associated workloads.
Benefits
[No benefits information provided]