AI/ML Ops Engineer (GPU Acceleration & AI Inference)

Role: AI/ML Ops Engineer (GPU Acceleration & AI Inference)

Location: Offshore Bangalore (BCIT)

Experience: 5+ Years / 7+ Years

We are looking for passionate AI/ML Ops Engineers to build and scale enterprise-grade AI platforms with a strong focus on GPU acceleration, inference optimization, and GenAI/LLM deployment.

Key Responsibilities

• Build and maintain containerized AI applications using Red Hat OpenShift, Kubernetes, and Helm.
• Deploy and optimize inference engines like NVIDIA Triton Inference Server and vLLM.
• Accelerate AI workloads using GPU optimization techniques (TensorRT/ONNX).
• Lead model deployment, lifecycle management, and monitoring in production.
• Implement observability using Prometheus and Grafana.
• Automate CI/CD pipelines using Jenkins, Terraform, Ansible, and Groovy.
• Develop automation tools using Python.
• Architect and deploy AI/ML platforms on Amazon Web Services (SageMaker & Bedrock knowledge is a plus).
• Contribute to GenAI, LLM, and Agentic AI initiatives.
• Build scalable, high-performance, and resilient AI platforms (on-prem & cloud).

Primary Skills

• AI/ML Ops & GPU Acceleration
• Production Model Deployment
• Kubernetes & OpenShift
• AWS Cloud Architecture

Secondary Skills (1+ year or strong knowledge)

• AI Inference optimization
• NVIDIA TensorRT
• ONNX
• Triton / vLLM