Manager | AI / ML | Delhi | Engineering | Hybrid Cloud Engineering
Deloitte Advisory2 days ago
Delhi, IndiaStaff+
Responsibilities
- Build and maintain on-premise hardware clusters, NVIDIA DGX systems, GPU nodes, and storage.
- Configure GPU scheduling, resource quotas, and Multi-Instance GPU (MIG) slices using Run:ai or Kubernetes.
- Deploy and optimize model-serving and inference backends including vLLM, Triton, and TensorRT-LLM.
- Implement containerization, networking, RBAC, and security monitoring for local AI workflows.
- Provide self-service Jupyter and Kubeflow environments for internal data science teams.
Requirements
- Be a full-time engineering graduate.
- Have deep Linux administration, Docker, and Kubernetes orchestration experience.
- Have hands-on NVIDIA CUDA, NCCL, and GPU performance-tuning experience.
- Have familiarity with model-serving runtimes, MLflow, Kubeflow, or Red Hat OpenShift AI.
- Be proficient in Python and infrastructure automation tools including Terraform and Ansible.
- Have 4 to 8+ years of experience in DevOps, Site Reliability Engineering, or AI infrastructure operations.
Benefits
- Hybrid work arrangement.
Tech Stack
Categories
About Deloitte Advisory
Deloitte Advisory provides consulting and managed services that help organizations manage risk, strengthen controls, investigate fraud, meet regulatory requirements, and execute transactions using analytics and industry expertise. Offerings span cybersecurity, M&A due diligence, finance and regulatory transformation, internal audit, and tech-enabled platforms. It is part of Deloitte’s global network (founded in 1845 and privately held), with U.S. member-firm teams serving corporations and government agencies across sectors.