What you'll be doing:
System Architecture & Flow Definition: Define and document comprehensive production, provisioning, update, recovery, and reset flows for AI factory sub-systems.
Ensure system-level architectural alignment and orchestrate seamless coordination between all the AI-Factory building blocks: GPU, DPU, CPU, Switch ASIC, NIC ASIC, BMC, and peripheral components.
Protocol Implementation & Guidance: Specify the use of standard management protocols (Red-Fish, NSM, PLDM, SPDM, MCTP, NC-SI) across sub-system interfaces to implement the management tasks.
Hardware/Software Intersect: Define system-level hardware and software behavior, including CPLD logic requirements, power-sequencing dependencies, and reset orchestration (e.g., handling PCIe PERST#, SBR, and forced resets).
Interface Management: Architect intra-board communication pathways using PCIe, I2C/I3C, USB, and SPI, ensuring robust out-of-band (OOB) and in-band management connectivity.
Cross-Functional Leadership: Collaborate with Production, Hardware and Firmware Engineering, ASIC FW/Driver teams, SW/NOS teams and QA to translate architectural specifications into implementable, testable solutions.
Technical Documentation: Author rigorous technical specifications, test plans, and architectural design documents to guide development and factory production.
What we need to see:
Deep System-Level Perspective: Proven ability to understand complex computing or networking systems top-to-bottom, with a background in networking architectures and efficiency and power saving methods.
Protocol Fluency: Strong working knowledge of modern platform management and security protocols.
Hardware Interface Knowledge: Familiarity with board-level communication buses (I2C, I3C, SPI, USB) and system interconnects (PCIe architecture, including link states and reset mechanisms).
Analytical Documentation Skills: Exceptional ability to write clear, unambiguous technical specifications, state-machine descriptions, and sequence diagrams.
Experience: BS/MS in Electrical Engineering, Computer Engineering, Computer Science, or a related field, with 5+ years of relevant industry experience.
Ways to stand out from the crowd:
Experience with power-saving methods.
Background with Redfish RESTful API definitions and OOB network infrastructure.
Familiarity with hardware RoT concepts and secure boot architectures.
Experience with production line tooling, factory provisioning, and manufacturing test flows.
Background in networking principles, Switch, NIC/SmartNIC data-plane and offload operations, or high-speed data center topologies.
