Alluri 770

DevOps & MLOps Engineer specializing in cloud-native infrastructure, Kubernetes, CI/CD and AI/ML deployment workflows across AWS and GCP. Skilled in automating CI/CD pipelines using GitLab CI/CD, Jenkins, Docker, and GitOps methodologies for scalable application deployments. Hands-on experience in deploying Agentic AI and LLM-based applications using Google ADK, Cloud Run, and Kubernetes, with expertise in monitoring and observability using Prometheus and Grafana, LLM fine-tuning using NVIDIA NeMo Customizer, and high-performance LLM inference deployment using NVIDIA Triton Inference Server.

DevOps & MLOps Engineer at Google (2026-01 – Present)

• Collaborated with ML and application teams to deploy Agentic AI applications developed using Google ADK and A2A architecture on Google Cloud Platform.
• Evaluated deployment strategies including Google Agent Engine, Cloud Run, and GKE, and recommended Cloud Run based on scalability, operational efficiency, and delivery timelines.
• Automated end-to-end CI/CD workflows using GitLab CI/CD and YAML-based pipelines for Docker image build, artifact registry integration, and Cloud Run deployments.
• Configured GitLab Webhooks to automatically trigger deployment pipelines on code commits and merge requests to streamline release workflows.
• Implemented containerized deployment processes enabling rapid and reliable application updates with minimal manual intervention.
• Managed deployment automation, troubleshooting, and operational support for cloud-native Agentic AI applications running on GCP environments.

DevOps & MLOps Engineer at Google (2025-04 – 2025-12)

• Worked on deploying NVIDIA NeMo Customizer for LLM fine-tuning workflows and NVIDIA Triton Inference Server for scalable LLM inference deployments.
• Managed containerized AI/ML workloads on Kubernetes environments ensuring reliable and scalable inference operations.
• Built and maintained monitoring dashboards using Prometheus and Grafana for real-time infrastructure observability and alerting.
• Performed model benchmarking and inference performance analysis using NVIDIA Perf Analyzer to optimize inference throughput and latency.
• Executed Kubernetes cluster upgrades, troubleshooting, deployment support, and operational maintenance across production cloud environments.

Bachelor of Technology in Computer Science and Engineering – Lovely Professional University Punjab (2021 – 2025)

12th with Science – Vikas Junior College (2019 – 2021)

10th with Science – Sri Chaitanya High School (2018 – 2019)