Staff Network Engineer – AI Fabric, Datacenter and Edge Networking

This is a fully remote position, open to applicants in Europe.

📋 Description

• Design, implement, and manage the network infrastructure that supports a GPU cloud platform for cloud gaming, artificial intelligence, and machine learning applications within telecom carrier networks.

• Create and maintain high-performance GPU networking fabrics and extensive RoCE fabrics.

• Enhance network performance for GPU communication patterns and east-west traffic.

• Establish reusable AI-fabric reference architectures and design principles.

• Develop and manage Layer-2 and Layer-3 datacenter networks utilizing scalable routing architectures.

• Ensure tenant isolation, manage ingress/egress routing, traffic management, and overlay networking.

• Deploy and oversee north-south security infrastructure, WAF protections, and platform security controls.

• Design private interconnects, dark fiber rings, high-capacity WAN connectivity, and global backbone integration.

• Lead end-to-end engineering delivery, from design and lab validation to production deployment.

• Validate network bills of materials, contribute to datacenter layouts and rack elevations, and manage capacity planning.

• Set deployment standards, validation criteria, rollback strategies, and reusable acceptance patterns.

• Take ownership of networking operational performance and reliability.

• Automate provisioning, configuration management, monitoring, and lifecycle management processes.

• Direct incident response and root-cause analysis for significant network events.

• Define and monitor SLAs, SLOs, reliability metrics, and operational benchmarks.

• Collaborate with infrastructure, platform, SRE, compute, storage, observability, and datacenter operations teams.

• Serve as the primary authority on networking design and influence the platform's networking roadmap.

• Mentor engineers and contribute to the development of the networking function.

⛳️ Requirements

• Extensive hands-on experience in designing and managing large-scale datacenter networks.

• Expert-level knowledge of BGP, OSPF, ECMP, and EVPN/VXLAN.

• Proven experience in operating high-speed Ethernet networks within production environments.

• Familiarity with NVIDIA/Mellanox networking platforms.

• Profound expertise in designing and managing networking fabrics for extensive GPU clusters and distributed AI workloads.

• In-depth understanding of NCCL communication patterns.

• Experience in tuning RoCE fabrics.

• Strong knowledge of RDMA transport behavior and potential failure modes.

• Practical experience in implementing and tuning PFC and ECN.

• Understanding of GPU collective communication patterns.

• Experience in designing rail-optimized GPU networking fabrics.

• Awareness of networking performance impacts on PyTorch and TensorFlow.

• Capability to debug cross-layer issues involving hardware, firmware, kernel networking, and distributed application communication layers.

• Strong knowledge of networking hardware, optics, and high-speed interconnects.

• Experience in designing network observability systems.

• Proficient automation skills using Python and/or Bash.

• Experience in applying software engineering practices to infrastructure automation.

• Proven ability to lead complex technical initiatives across different teams.

• Demonstrated capability to set architectural direction and promote the adoption of engineering standards.

• Strong mentoring skills.

• Experience in owning architecture and direct implementation in lean or rapidly scaling environments is highly preferred.

🏝️ Benefits

• Competitive compensation package that reflects your skills and experience.

• Flexible working environment.

• Hybrid-friendly work arrangements.

• International and diverse workplace culture.

• Opportunities for career advancement in a rapidly growing scale-up.