Senior Staff Design Automation Engineer
Groq- Full Time
- Senior (5 to 8 years)
Candidates should have a Bachelor's degree in Electrical Engineering, Computer Engineering, or a related field, with a Master's degree preferred. A minimum of 5+ years of experience in FPGA design and verification is required. Expertise in hardware design using Hardware Description Languages (HDLs) like Verilog or VHDL is essential. Familiarity with RISC-V architecture and embedded systems development is needed, along with an understanding of hardware-software integration concepts. Experience with scripting languages like Python for test automation is necessary, as well as knowledge of industry-standard management protocols (MCTP, PLDM, SPDM) and platform BMC. Candidates should also possess strong analytical and problem-solving skills, excellent communication, collaboration, and teamwork abilities, and knowledge of power management techniques (PMBus) and hardware security concepts.
The FPGA Design Engineer will design and verify FPGA-based solutions for AI inference accelerator management and define FPGA microarchitecture specifications while collaborating with stakeholders. They will develop resilient dual boot architecture for multi-core multi-chiplet booting, design and implement hardware and software modules for platform power management, health monitoring, and telemetry data acquisition. The role includes interfacing with host server BMC through SMBus mailbox, integrating RISC-V CPU cores and related firmware into FPGA designs, and developing an eFuse controller within the FPGA. Additionally, they will design and integrate a secure boot solution adhering to NIST standards, collaborate with cross-functional teams for hardware-software integration, and author Python scripts for hardware testing and automation.
AI compute platform for datacenters
d-Matrix focuses on improving the efficiency of AI computing for large datacenter customers. Its main product is the digital in-memory compute (DIMC) engine, which combines computing capabilities directly within programmable memory. This design helps reduce power consumption and enhances data processing speed while ensuring accuracy. d-Matrix differentiates itself from competitors by offering a modular and scalable approach, utilizing low-power chiplets that can be tailored for different applications. The company's goal is to provide high-performance, energy-efficient AI inference solutions to large-scale datacenter operators.