AI Infrastructure Benchmarking and Network Validation Engineer
Core
Plan, execute, and analyze comprehensive benchmarks on Cisco switches to ensure optimal AI/ML network operations, including throughput, latency, congestion, and failover.
Role type
AI Infrastructure Benchmarking and Network Validation Engineer
Builds
Scalable, high-performance, and resilient network fabrics for AI/ML workloads
Domain
Networking, AI Infrastructure, Hyperscale Cloud
Deliverable
production ML models | infrastructure
Required skills
Python for automation, L2/L3 network protocols (BGP, OSPF, EVPN, VxLAN, IPv6), Traffic tools (Spirent, IXIA), Docker or Kubernetes, network testing and validation
Preferred skills
SONiC, NxOS, Linux, Leaf-spine fabric troubleshooting, Cisco Nexus Dashboard, complex network segmentation, RDMA, RoCEv2, PFC, ECN, congestion control, QoS, buffer behavior, lossless Ethernet
Technologies
SONiC, NX-OS, Ansible, Python, Bash, Git, NCCL, RCCL, ib_write_bw, ib_read_bw, ib_send_bw, ib_write_lat, netperf, iperf, MPI, OSU benchmarks
Responsibilities
Define rigorous benchmark methodologies, test plans, KPIs, and reporting structures for AI RoCE Ethernet fabrics; Run and analyze performance tests using industry-standard tools; Validate switch ASIC features including buffers, schedulers, QoS/queuing, ECMP behavior, and telemetry; Own switch OS configuration and automation to implement advanced features like SRv6 and segment routing; Document PoC architecture, benchmark methodologies, topology diagrams, configurations, results, findings, and recommendations
Seniority
Senior, hands-on IC
