19 Aug
|
Yochana
|
Canada
Title: Senior ASIC/NIC Network Validation Engineer – RDMA & AI Networking - REMOTE
Job Summary:
We are seeking a highly experienced ASIC/NIC Validation Engineer to develop and execute tests for networking silicon supporting large-scale distributed AI workloads. The role focuses on RDMA, RoCE v2, NCCL collective communications, networking ASICs/NICs, and multi-node validation across emulation, FPGA, and silicon platforms.
Key Responsibilities:
- Develop and maintain tests for AllReduce, AllGather, ReduceScatter, and AllToAll operations.
- Create RDMA Verbs-level tests covering positive, negative, and error scenarios.
- Validate multi-node and multi-NIC communication across different network topologies.
- Develop traffic-generation and data-validation tools for RDMA workloads.
- Automate testing using C/C++ and Python and integrate tests into CI/CD pipelines.
- Execute and analyze NCCL-tests, perftest, and RDMA benchmarks .
- Debug issues across ASIC RTL, firmware, drivers,
rdma-core, and user-space communication libraries.
- Work with architecture, firmware, driver, modeling, and validation teams.
Required Skills:
- 10+ years in test development, silicon validation, or networking.
- 5+ years testing networking ASICs, NICs, SmartNICs, or DPUs.
- 5+ years with collective communication/distributed systems.
- Expert C/C++ and solid Python .
- Strong knowledge of RDMA, RoCE v2, NCCL/MPI, Ethernet/L2, PCIe, and collective operations .
- Experience with ASIC/silicon validation and preferably emulation/FPGA environments.
- Knowledge of QPs, CQs, MRs, PDs, RDMA READ/WRITE/SEND/RECEIVE.
- Experience with libibverbs/rdma-core is highly desirable.
Education: B.S./M.S. in Computer Science, Electrical Engineering, Computer Engineering, or a related field.
📌 Network Validation Engineer - REMOTE (Canada)
🏢 Yochana
📍 Canada