Director of Backend Engineering (AI Infrastructure)

Job Summary

We are seeking a visionary Director of Backend Engineering to lead the teams responsible for the software "brain" that manages our global AI Physical Infrastructure. You will oversee the development of the SDN orchestrators, automated fleet management systems, and the high-performance storage backends that power our AI training and inference clusters.

Your mission is to abstract the complexity of specialized hardware (NVIDIA/HPC) into a seamless, automated, and hyper-reliable cloud platform.

Responsibilities

- Strategic Leadership &
- Fleet Orchestration: Software-Defined Infrastructure: Lead the design and delivery of an SDN Orchestrator to automate complex GPU networking (InfiniBand/RoCE/NVLink) and core DC routing.

- Fleet Health Automation: Oversee the development of backend services for GPU Health &

- Fault Detection, automating the lifecycle from burn-in and diagnostics to global RMA workflows.

- Capacity &

- Traffic Engineering: Drive the backend logic for global traffic routing, load balancing (NGINX/Kong), and IPAM to ensure zero-bottleneck training environments.

- Data &

- Storage Systems: HPC Data Pipelines: Collaborate with storage engineers to build backend interfaces for Parallel File Systems (Lustre, Weka, VAST etc.), ensuring high-throughput data delivery to compute nodes.

- Storage Durability: Direct the backend strategy for AI Object Storage, focusing on high durability and low-latency retrieval for massive datasets.

- Engineering Excellence: Scalable Architecture: Act as the final technical authority for AI Infra Architecture, ensuring systems are resilient, multi-region, and capable of sub-millisecond coordination.

- DevOps &





- IaC Culture: Champion a "Hardware-as-Code" mindset, utilizing Python, Ansible, and Terraform to eliminate manual intervention in DC operations.

- Team Development: Lead a multi-disciplinary org including Backend Developers, SDN Engineers, and Infra Ops teams, AI Infra Engineering.

- Establish 24/7 L1/L2/L3 operational standards to maintain > 99.99% availability of the AI fleet.

Requirements

- Experience: 15+ years in Backend Engineering, with at least 5 years in a leadership role managing complex infrastructure (Cloud, FinTech, or HPC).

- Deep Infrastructure Knowledge: Proven experience with Linux internals, hardware-software interfaces (drivers/firmware), and distributed systems.

- Networking Mastery: Solid understanding of L2/L3 networking, and ideally, specialized fabrics like InfiniBand or RoCE.

- The Stack: Skilled proficiency in Python, Go, or C++, and deep experience with Terraform, Kubernetes, and Ansible.

- Large-Scale Data: Experience managing high-performance storage backends (GPFS, Lustre, or equivalent parallel systems).

- Hardware Savvy: You don't just write code; you understand power envelopes, liquid cooling constraints, and GPU architecture (NVIDIA/HPE/Dell).

Skills

- Experience building custom SDN controllers or orchestration layers from scratch.

- Direct experience with NVIDIA or GPUDirect technologies.

- Previous success in a "Hyper-scale" environment (AWS, Azure, GCP, Meta, AI Clouds etc.).

Locations

- Bengaluru

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 Director - Backend Engineering - AI Infra (Bengaluru)
🏢 Coupang
📍 Bengaluru