About the Role

Own end-to-end validation of our AI rack-scale systems. You'll take systems from board and tray bring-up to full racks and multi-rack clusters, through L11 rack integration and deployment in the field. That includes accelerator compute trays, host servers, scale-up switches, and the components that tie them together: NICs, retimers, cables, power shelves, busbars, liquid cooling, and rack management. You'll build the plans, environments, and automation that prove our systems work at fleet scale. You'll partner with silicon, hardware, firmware, software, and manufacturing teams, along with our ODM and CM partners.

What You'll Do

Create system validation plans for AI rack-scale systems at the board, tray, rack, and multi-rack cluster levels, through L11 rack integration
Build validation environments, including system diagnostics, stress and burn-in tests, workload-based tests, fleet health checks, and rack acceptance tests
Develop test automation that scales execution and automated triage across hundreds of racks and thousands of trays, including telemetry collection, results databases, and dashboards
Lead system and rack bring-up from first power-on of trays and racks through full validation, including interoperability across compute, host, and switch trays, power, thermal and performance characterization, margin testing, and long-duration stability and reliability
Drive validation through each NPI phase (Proto, EVT, DVT, PVT, and production) and define entry and exit criteria for each
Debug and root-cause issues across silicon, board, firmware (BIOS/UEFI, BMC, device firmware), OS and drivers, networking, power, and thermal
Drive the NPI and production ramp: define L6, L10, and L11 test content and acceptance criteria with ODM and CM partners, improve factory test yield, and support data center bring-up, field deployment, field failure analysis, and RMA
Partner with silicon validation, board and system hardware, thermal, firmware, software, networking, manufacturing and test engineering, ODM and CM partners, suppliers, and data center operations

What We're Looking For

5+ years of experience in system validation, system integration, or bring-up for servers, accelerators, or rack-scale systems
Strong coding skills in Python, C, and C++, plus solid Linux systems experience
Experience with BMC (OpenBMC), Redfish, and IPMI
Proven system and rack bring-up experience, from first power-on through full validation
Experience validating hardware through NPI phases (Proto, EVT, DVT, PVT) and into production
Experience working with ODM and CM partners on L6/L10/L11 test content, acceptance criteria, and factory yield
Strong debug skills and fluency with tools such as PCIe and Ethernet protocol analyzers, oscilloscopes, logic analyzers, JTAG debuggers, and BMC logs and telemetry
Experience building test automation, telemetry, and triage infrastructure at fleet scale
Deep expertise in one or more of the following:
AI training and inference workloads and collectives at scale
PCIe Gen5/6/7, CXL, PCIe switches, and retimers
Scale-up fabrics and switches
112G/224G SerDes, copper cables and backplanes, and optics
Scale-out networking, RDMA, and RoCE
Rack power delivery and power management
Liquid cooling and thermal
System management and firmware update
RAS and error handling
Secure boot
System performance
Strong collaboration and communication skills across internal teams, manufacturing partners, and data center operations

Full compensation packages are based on candidate experience and relevant certifications.

California pay range

$250,000—$300,000 USD

Compensation

Final offers depend on level, location, and skills relevant to the role. Additional compensation: equity grant per company guidelines; medical / dental / vision; 401(k); standard PTO.

Visa Sponsorship

DensityAI sponsors qualified candidates for H-1B, O-1, TN, E-3, and other employment-based visas, and we welcome applicants on F-1 OPT and STEM-OPT. Work authorization is required at start; we provide immigration support to secure or transfer status.