PROJECT DIRECTORY / CLOUD · DEVOPS · AI · SOFTWARE
Practical work. Clear evidence.
AWS hosting and operations labs, delivery automation, AI applications and full-stack systems—organized by the engineering work involved.
Each case study distinguishes implemented code, documented lab work and unverified runtime results.
13 projects
01 / CLOUD & DEVOPSDeployed portfolio
AWS Portfolio & Serverless Contact
A public portfolio with private-origin delivery and an AWS contact integration.
The problem A static website needs HTTPS delivery, controlled origin access and a contact channel without a dedicated application server.
Project work Built the static application and contact integration; documented private S3/CloudFront hosting and the Lambda/SES backend during Cloud and DevOps practical work.
From a web application to a repeatable Linux container deployment.
The problem A restaurant application needed a consistent build/start workflow and a workable host/container port arrangement.
Project work Containerized the Velvet Restaurant application with Nginx, deployed it on EC2 Ubuntu and used a Bash deployment script to rebuild and restart the container.
AWS agent orchestration connecting policy retrieval with business-workflow tools.
The problem A support workflow needs to combine policy knowledge with order/inventory actions while tracking the request across tools.
Project work Developed Python multi-agent orchestration with Bedrock/Strands integrations, Knowledge Base retrieval helpers and DynamoDB/Lambda workflow tools.
From word embeddings to retrieval-grounded PDF conversations.
The problem Finding useful information in text and PDFs requires retrieval of relevant context and a clear response when evidence is missing.
Project work Implemented custom GloVe/search components, a retrieval pipeline with abstention behavior and Gemini-powered PDF chat with conversation context and source references.
A conversational assistant with streaming responses and organized chat history.
The problem A useful chat interface needs more than a model call: conversation management, response controls and understandable storage boundaries matter.
Project work Built the Streamlit chat interface, Gemini streaming integration, response-style/temperature controls and conversation create/search/rename/delete flows.