Systems Engineer, Data Center Debug

Job Title

Systems Engineer, Data Center Debug

Role Summary

Lead post-silicon debug and system-level failure analysis for Tenstorrent's AI accelerator platforms. Work across silicon, boards, firmware, drivers, and system software to diagnose and resolve hardware and firmware issues.

Hybrid role based in Toronto, Canada; collaborate with ASIC, firmware, and software teams and develop tools and methodologies to improve platform reliability.

Experience Level

Mid-level. Candidates at various experience levels will be assessed during interview and offers will align to the evaluated level.

Responsibilities

Primary responsibilities include post-silicon system debug, failure analysis, and building diagnostic infrastructure.

• Lead post-silicon debug across AI accelerator platforms at chip, board, and system levels.
• Diagnose power, thermal, GDDR/DDR, PCIe, Ethernet/SerDes, NoC, and firmware-related failures.
• Develop Python and C diagnostic tools, automation, and debug frameworks.
• Use lab equipment (oscilloscopes, logic analyzers, protocol analyzers) for investigations.
• Analyze schematics, register states, telemetry, and firmware behavior to determine root cause.
• Work cross-functionally with ASIC, firmware, software, and validation teams to drive fixes and mitigations.

Requirements

Focused, hands-on technical skills needed for success.

• Experience in hardware debug and post-silicon bring-up for CPU, SoC, or ASIC systems.
• Strong understanding of processor architecture and microarchitecture (RISC-V, x86, or ARM) and familiarity with debug/trace methodologies (e.g., iJTAG).
• Proven ability to diagnose complex hardware, firmware, and software interactions through root-cause analysis.
• Practical experience with lab instrumentation and debugging tools (oscilloscopes, logic analyzers, protocol analyzers).
• Experience developing diagnostic and automation code in Python and C.
• Effective collaborator across ASIC, firmware, software, and validation teams.
• Employment contingent on eligibility to access U.S. export-controlled technology; ability to satisfy export compliance requirements may be required.

• Experience with GDDR/DDR, PCIe, Ethernet/SerDes, NoC, or power-management debugging.
• Prior work on AI accelerators, high-performance CPUs, or complex SoCs.
• Familiarity with system-level telemetry and large-scale debug infrastructure.

Education Requirements

Not specified.

About the Company

Company: Tenstorrent

Headquarters: Austin, Texas, United States

Tenstorrent is a technology company focused on designing innovative computing solutions. They are known for their expertise in the development of advanced hardware, including ASICs and SoCs, aimed at enhancing performance and efficiency in various applications.