Showcasing my work in DevOps, Cloud, and AI/ML
Architected a complete RAG pipeline using Amazon Bedrock Knowledge Bases to automate the data ingestion workflow, including data retrieval from an S3 bucket. Utilized the Titan Text Embeddings model to convert source documents into vector embeddings and stored them in an Amazon Aurora Serverless (PostgreSQL) Vector database for efficient similarity search and retrieval. Developed the chatbot's core logic in Python using LangChain, integrating the AmazonKnowledgeBasesRetriever to fetch relevant content from the vector store.
Designed and deployed a serverless Python application using AWS Lambda, integrated with API Gateway for RESTful API access. Implemented secure data access between Lambda and external databases through private subnets and VPC connectivity.
Designed and deployed a Kubernetes cluster using Amazon Elastic Kubernetes Service (EKS) with managed node groups for high availability. Configured multi-AZ deployment with public and private subnets, NAT Gateway, and security groups ensuring secure communication and internet access.
Automated infrastructure provisioning using Terraform, deploying an end-to-end CI/CD pipeline on AWS integrating EKS, CodeBuild, CodePipeline, ECR, and S3. Designed a modular Terraform architecture to create and manage S3 buckets, ECR repositories, and EKS clusters.
Building a unified platform to manage Kubernetes clusters across AWS, Azure, and GCP
Developing an ML-based system to automatically optimize cloud infrastructure costs and performance
Creating a comprehensive GitOps framework for enterprise-scale deployments