Director | AI / ML | Delhi | Engineering | Hybrid Cloud Engineering
• Job requisition ID : 111374
• Location: Delhi
• Entity: Deloitte Touche Tohmatsu India LLP

The Team

The team drives large-scale mainframe modernization and enterprise transformation for Tier-1 global banks. It combines deep technical expertise with business development and delivery leadership to modernize legacy platforms, accelerate cloud adoption, and build future-ready digital capabilities for global financial institutions.

Your work profile

- Build and maintain on-premise GPU infrastructure, including NVIDIA DGX systems, GPU clusters, and storage.

- Configure GPU scheduling, resource quotas, and multi-instance GPU (MIG) using Kubernetes or Run.

- Deploy and optimize model serving platforms such as vLLM, Triton, and TensorRT-LLM.

- Manage containerization, networking,



access controls, and security monitoring for AI workflows.

- Provide self-service AI development environments using Jupyter and Kubeflow.

Key skills required:

- Full time Bachelor's degree in Engineering with 15+ Years of Exp

- 4–8+ years of experience in DevOps, SRE, or AI infrastructure operations.

- Strong expertise in Linux administration, Docker, and Kubernetes.

- Hands-on experience with NVIDIA CUDA, NCCL, and GPU performance tuning.

- Familiarity with model serving runtimes, MLflow, Kubeflow, or Red Hat OpenShift AI.

- Proficiency in Python and infrastructure automation tools such as Terraform and Ansible.

📌 Director | AI / ML | Delhi | Engineering | Hybrid Cloud Engineering
🏢 Deloitte
📍 Delhi