We are looking for a Network Engineer to design, deploy, and troubleshoot high-throughput, low-latency networks that support large-scale AI training and inference workloads. In this role, you’ll work at the intersection of high-performance computing and hyperscale infrastructure, enabling next-generation AI systems through robust and scalable networking solutions.
You’ll leverage advanced networking protocols and technologies—such as RoCEv2, Infiniband, and smartNICs—while applying foundational expertise in L2/L3 networking, telemetry, and diagnostics. A strong background in Linux-based systems, network automation (Python, Ansible, Terraform), and performance tuning is essential. This is a high-impact opportunity to shape the backbone of AI infrastructure at hyperscale.
Responsibilities:
Design and deploy high-throughput, low-latency network systems to support AI training and inference infrastructure.
Troubleshoot and optimize Linux-based networking stacks across thousands of nodes.
Tune Linux kernel networking parameters for performance(RQ affinity, socket buffers, MTU, etc.).
Automate network provisioning, monitoring, and diagnostics using Python, Ansible, Terraform, or equivalent tools.
Implement and manage L2/L3 network topologies, including EVPN-VLAN, BGP, OSPF, and static routing.
Support and troubleshoot Infiniband, RoCEv2, SR-IOV, and/or smartNIC-based deployments.
Analyze performance metrics to identify and resolve packet loss, congestion, jitter, and other network anomalies.
Integrate telemetry and logging solutions using tools such as Prometheus, Grafana, and sFlow/NetFlow.
Collaborate with security and platform teams to enforce network segmentation, ACLs, and policy enforcement.
Participate in design reviews, capacity planning, and incident response for critical infrastructure.
Travel may be required for this role.  The amount of travel will vary from 25% to 100% depending on business need and client requirements.