• Define the end-to-end architecture for AI platforms, from node-level design to rack-scale composable systems • Drive adoption of PCIe/UAlink-based fabrics for disaggregated compute, memory, and accelerator scalability • Architect solutions for GPU/accelerator-dense systems optimized for AI training and inference workloads • Lead integration of connectivity solutions — retimers, switches, and fabric controllers — aligned with Astera Labs' product ecosystem • Lead system architecture and design for high-performance compute platforms optimized for AI and accelerator-driven workloads • Define and implement GPU-enabled server platforms for AI training, inference, and HPC workloads • Define the technical vision and multi-year product roadmap for AI infrastructure platforms.

• Perform firmware updates and lifecycle management for server hardware • Troubleshoot hardware and infrastructure-related issues (servers, components, connectivity) • Support provisioning and decommissioning of bare metal servers • Work with out-of-band management interfaces (IPMI / iDRAC / iLO or similar) • Apply and maintain hardware configuration standards and profiles • Participate in incident response and root cause analysis • Contribute to development of operational processes and documentation (SOPs) • Collaborate with infrastructure, network and devops teams • Participate in evaluation and selection of hardware configurations (CPU, RAM, storage, components) • Contribute to infrastructure scaling and hardware standardization • Participate in on-call rotations

• Gather and analyze requirements from clients. • Consult clients and internal teams on solutions, stacks, and tools. • Plan, develop, and implement firmware. • Work alongside our mobile teams to streamline, optimize, or sometimes troubleshoot communication between device and companion applications. • Test firmware releases. • Write and maintain firmware documentation. • Estimate your work. • Participate in the requirement discussion meetings and daily calls, providing feedback on inconsistencies and open issues. • Spearhead better practices, and ensure standards are set and followed. • Participate in knowledge-sharing activities within and outside of intent.

Role Description In this role, you will be responsible for DVT (Design Verification Testing) and Sustaining for early-stage validation and bring-up of Tensordyne’s next-generation hardware products for generative AI inference acceleration. You will drive hardware bring-up for new designs, debug issues, and ensure all systems meet performance and reliability specifications. Responsibilities include: - Creating and executing hardware test plans - Validating functionality - Identifying and root-causing failures - Making design changes - Managing part lifecycle - Building and maintaining benchtop test environments - Supporting reliability and stress testing across Tensordyne’s hardware portfolio Qualifications - B.S. degree in Electrical or Computer engineering - 5+ years of hardware validation and/or sustaining experience on board and system level products - Experience in creating test setups, writing test plans and reports - Strong knowledge of oscilloscopes, DMMs, power supplies, in-system programmers and analyzers - Demonstrable experience with EVT, DVT, PVT testing and certification processes - Self-starter and highly motivated to work in a dynamic start-up environment Requirements - Support all aspects of hardware system validation and sustaining of Tensordyne’s board and system level products - Gather requirements and specifications from engineering, product and operations teams for planning Hardware Validation and creating Test Plans - Hands on responsibility for board bring up, programming, performing functional test and design verification and board characterization - Support Compliance testing activities - Drive hardware parts selection and vendor qualification processes in collaboration with manufacturing operations - Analyze failures and find root causes for issues and drive them to resolution - Make necessary design changes and drive ECO/MCO releases - Support Diagnostic and Manufacturing Test development activities - Develop scripts and tools to automate test procedures and data analysis Benefits - Comprehensive benefits - Competitive compensation - Flexible spending options - Recognition programs Company Description Tensordyne is an AI system solution company that builds very high-performance, low-power generative AI inference systems. Our mission is to enable multimodal Generative AI inference acceleration at scale, with safe, sustainable, high-performance systems for our hyperscaler and neocloud data center customers. We are at the leading edge of advancing the latest research and product improvements for generative AI inference solutions. Tensordyne is a well-funded, fast-paced startup company with headquarters in both Sunnyvale, CA, and Munich, Germany. We also have many talented team members working remotely across North America and Europe. Tensordyne is an equal opportunity employer. We believe that a diverse team is better at tackling complex problems and coming up with innovative solutions.