Senior Ethernet Performance Engineer

Cornelis Networks, Inc.•San Francisco, CA

6d•Remote

About The Position

Cornelis Networks is seeking a Senior Ethernet Performance Engineer to lead performance validation, debug, and characterization of our next-generation Ethernet-based networking silicon products. This role involves both internal validation and collaboration in customer environments, focusing on post-silicon bring-up, lab-based performance validation, and optimizing system performance with customers. It's a high-impact, cross-functional position with visibility across silicon design, system architecture, software, and customer engineering teams.

Requirements

7+ years of experience in post-silicon validation, performance engineering, or silicon debug for networking or high-performance compute products.
Strong understanding of networking protocols and technologies (e.g., Ethernet, PCIe, switching, congestion control), PFC, ECN, DCQCN.
Familiarity with data center performance requirements and benchmarks.
Scripting and automation skills (Python, Shell, etc.).
Excellent problem-solving and cross-functional communication skills.
Comfort working directly with customers, field engineers, and technical partners.

Nice To Haves

Deep understanding of networking and memory data flows, including technologies such as DPDK, RDMA, or similar high-performance I/O frameworks.
Background in silicon performance modeling, system architecture, or firmware/hardware co-design.
Exposure to cloud-scale workload analysis and performance tuning
Experience running HPC (MPI application benchmarks) & AI (NCCL/RCCL benchmarks).
Telemetry & Debugging: Investigating PFC deadlocks, packet drops, line-rate throughput, and tail latency using kernel tools, packet captures, and fabric telemetry.

Responsibilities

Building, configuring, and benchmarking Ethernet fabrics with RoCEv2 (RDMA over Converged Ethernet) to perform head-to-head performance evaluations against other network architectures (InfiniBand, Omni-Path, and rival Ethernet solutions).
Develop and execute validation and performance test plans targeting both internal lab and real-world data center deployment scenarios.
Analyze performance metrics such as throughput, latency, congestion, power efficiency, and architectural behavior under networking workloads.
Work directly with customers and field teams to reproduce, debug, and optimize performance issues in production environments.
Create diagnostic tools and scripts to collect, analyze, and visualize performance data.
Collaborate with architecture, firmware, and software teams to root-cause performance anomalies and recommend hardware or system-level improvements.
Translate validation and debug findings into actionable feedback for silicon and systems design.
Provide technical guidance and support to customers integrating and tuning our products in their data center infrastructures.