ASIC Engineer, Accelerator Systems
Description
Meta is seeking a highly skilled and experienced ASIC Systems Engineer to join our team. As a key member of our engineering team, you will be responsible for designing, developing, and maintaining system tools/drivers/drivers, diagnostics SW and performance optimization/benchmarking toolsthat support Meta's advanced AI accelerator ASIC in production.
Responsibilities
Design, develop, and maintain system/diagnostics tools/services/libraries to support the ASIC Develop diagnostics tools to troubleshoot and debug issues with the ASIC and related software components Optimize and benchmark the performance of the ASIC and related software components Collaborate with hardware engineers to understand the ASIC architecture and design Collaborate with software engineers to integrate the ASIC into the overall software stack Participate in code reviews and contribute to the development of best practices Stay up-to-date with the latest developments in Linux kernel development and related technologies
Qualifications
BS/MS in Computer Science or a related field 5+ years of experience in Linux system SW development and embedded FW development Proficient in C and C++ programming with deep technical expertise Experience with some of the following modules/domains: PCIe, Networking, Flash, Memory, CPU, GPU, DRAM (DDR4/5 or HBM) Experience of developing diagnostic/telemetry tools and RAS features Knowledge of computer architecture and hardware design principles Experience with performance optimization and benchmarking Exceptional problem-solving skills and proven ability to work independently Excellent communication skills, both written and oral Experience of working on a HW product Experience of working with HW tools including architecture models, emulation platforms and FPGA environment (VCS, Palladium, Protium, Zebu, Veloce, Cadence, Mentor, Synopsys) Experience with AI accelerator ASICs Experience with continuous integration and continuous deployment (CI/CD) pipelines Experience with performance optimization and benchmarking Experience of developing RAS features for a product