Impact-driven Platform Engineer with 5 years of experience designing and deploying scalable infrastructure, MLOps pipelines, and GenAI systems across cloud-native environments. Specialized in ML model lifecycle management, GenAI/LLM deployments, and edge-to-cloud integration. Proven expertise in tools like MLFlow, VertexAI Pipelines, Kubeflow, Triton Inference Server, and NVIDIA Riva & Tokkio. Proficient at orchestrating GPU-backed inference services on Kubernetes, automating CI/CD workflows, and driving performance and cost optimization in both development and production-scale environments.