Seeking a seasoned Director to lead AI/ML initiatives within our Engineering team in Delhi. This role focuses on establishing and managing robust hybrid cloud infrastructure essential for advanced artificial intelligence and machine learning operations. The position requires a blend of strategic oversight and hands-on technical expertise to drive innovation and efficiency.

This is an opportunity to shape the future of our AI/ML platform by building and optimizing the underlying infrastructure. You will be instrumental in ensuring our data science teams have the resources and tools needed to develop cutting-edge AI solutions.

Spearhead the development and maintenance of on-premise hardware clusters, including NVIDIA DGX and GPU nodes, alongside storage solutions.

Implement and manage GPU scheduling, resource quotas, and multi-instance GPU (MIG) slices utilizing tools such as Run:ai or Kubernetes.

Deploy and fine-tune inference backends like vLLM, Triton, or TensorRT-LLM for optimal model serving performance.

Oversee platform operations, encompassing containerization, networking, Role-Based Access Control (RBAC), and security monitoring for local AI workflows.

Empower internal data science teams by providing accessible self-service environments, including Jupyter and Kubeflow.

A full-time engineering graduate with 4-8+ years of experience in DevOps, SRE, or AI infrastructure operations.

Proficiency in core technologies: Deep Linux administration, Docker, and Kubernetes (K8s) orchestration.

Demonstrated experience with NVIDIA CUDA, NCCL, and GPU performance tuning.

Familiarity with MLOps/LLMOps tools and concepts, including model serving runtimes, MLflow, Kubeflow, or Red Hat OpenShift AI.

Strong programming skills in Python and experience with infrastructure automation tools like Terraform and Ansible.