Full-Stack Developer · AI Platforms & Agents
JayPatel
I build AI-powered platforms that ship — owning everything from pixel to pipeline.
About
I'm Jay — a full-stack developer building enterprise AI applications at scale.
I work end-to-end: designing the interface, building the backend, integrating AI systems, and shipping the infrastructure that runs it all. Right now I'm diving deeper into AI agents and what's possible at the frontier.
Currently working with
Writing
Authenticating MCP Clients to a Remote Server: Why DCR Fails on Cognito, and What Works Instead
The MCP spec says a client should discover the auth server and dynamically register itself. Cognito supports neither half of that. This is the war story of getting Kiro, Claude, claude.ai, and VS Code Copilot all authenticated to one remote MCP server behind Cognito — the DCR dead end, the static client-ID path that works, and the per-client quirks that only surface live.
Building an MCP App: An Interactive Kanban Board the LLM Can Drive
How I built an interactive Kanban board as an MCP App — a UI served by an MCP server and rendered inside the chat — then deployed it to Bedrock AgentCore behind a Gateway. The interesting parts weren't the happy path: a widget-per-tool-call render bug, latency-zero drag races, and a /tmp SQLite store that silently reset on every call.
How AWS Lambda Works Under the Hood
A deep dive into how Lambda actually runs your code — Firecracker microVMs, the invoke path, the Assignment and Placement services, cold starts, lazy-loading 10 GB container images, and SnapStart.
Selected Work
MagicDot Solar
Node.js, MongoDB, Handlebars, Docker, Kubernetes, Jenkins, Terraform, SonarQube, Prometheus
- Full-stack web application for a solar energy company with dashboards for employees and customers, built with Node.js, Express.js, MongoDB, and Tailwind CSS.
- Streamlines solar operations including task handling, customer support, sales, contract management, and crew task management.
- CI/CD pipeline with Jenkins, SonarQube, Docker, and deployment to AWS EKS via ArgoCD.
- Infrastructure as Code with Terraform; monitoring via Prometheus and Grafana.
AWS Resource Manager
React, Django, Terraform
- Full-stack app (Django + React) for automated AWS resource cleanup, optimizing infrastructure utilization and reducing costs.
- Automated deletion of unused AMIs, EBS volumes, ECR repos, ECS/EKS clusters, IAM users, key pairs, RDS snapshots, and security groups via configurable retention policies.
- Infrastructure drift detection by parsing Terraform state files against live AWS resources.
- Intuitive React UI for resource selection, drift detection, and cleanup status.
AWSDriftGuard
Python, Boto3, Terraform
- CLI tool to detect drift between live AWS infrastructure (EC2, S3, RDS, IAM Roles, etc.) and Terraform state files.
- Integrated Slack API for automated drift notifications to team channels.
- Supports 'detect' mode (console output) and 'report' mode (Slack integration) with comprehensive drift reports.
Index / More work
Education
Stevens Institute Of Technology
Candidate for Masters in Computer Science (MSCS) · Hoboken, NJ
Coursework —Cloud Computing, Agile Methods for Software Development, Artificial Intelligence, Data Analytics & Machine Learning, Database Management Systems
Gujarat Technological University
Bachelor in Computer Engineering · Anand, India
Coursework —Data Mining & Business Intelligence, Artificial Intelligence, Mobile communication and Networking, System Programming, Information & Network Security
06 / What's next
Let's build something that ships.
My inbox is always open — for roles, collaborations, or just to talk about agents. I'll get back to you.