Full-Time
FPGA Design Engineer
Confirmed live in the last 24 hours
AI compute platform using in-memory computing
Data & Analytics
Hardware
AI & Machine Learning
Mid, Senior
Santa Clara, CA, USA
Required Skills
Verilog
Python
Management
Mergers & Acquisitions (M&A)
VHDL
FPGA
Requirements
- Bachelor's degree in Electrical Engineering, Computer Engineering, or a related field
- Minimum of 5+ years of experience in FPGA design and verification
- Expertise in hardware design using Hardware Description Languages (HDLs) like Verilog or VHDL
- Familiarity with RISC-V architecture and embedded systems development
- Understanding of hardware-software integration concepts
- Experience with scripting languages like Python for test automation
- Strong analytical and problem-solving skills
- Experience with industry-standard management protocols (MCTP, PLDM, SPDM)
- Experience with platform BMC (Baseboard Management Controller)
- Knowledge of power management techniques (PMBus)
- Knowledge of hardware security and secure boot concepts
- Experience with cloud server architectures and concepts
Responsibilities
- Design and verify FPGA-based solutions for d-Matrix AI inference accelerator management
- Define FPGA microarchitecture specifications and collaborate with stakeholders to ensure alignment with project requirements
- 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
- Interface with host server BMC through SMBus mailbox with management protocol overlays such as MCTP, PLDM and SPDM
- Integrate RISC-V CPU cores and related firmware into FPGA designs
- Develop eFuse controller within the FPGA
- Design and integrate a secure boot solution adhering to NIST standards within the FPGA to enable secure booting of d-Matrix accelerator chiplets
- Collaborate with cross-functional teams to ensure seamless hardware-software integration and support inference accelerator hardware bring-up and troubleshooting
- Author Python scripts for hardware testing and automation
d-Matrix is developing a unique AI compute platform using in-memory computing (IMC) techniques with chiplet level scale-out interconnects, revolutionizing datacenter AI inferencing. Their innovative circuit techniques, ML tools, software, and algorithms have successfully addressed the memory-compute integration problem, enhancing AI compute efficiency.
Company Stage
Series B
Total Funding
$161.5M
Headquarters
Santa Clara, California
Founded
2019
Growth & Insights
Headcount