Developer / Engineer / Creator
Engineer • Designer • Creator • Visionary •Engineer • Designer • Creator • Visionary •
NO.02
Capabilities
Tech_Stack
001Spec_Sheet
Frontend
HTML5/CSS/JSTypescriptReactNext.jsSASSTailwind CSS
002Spec_Sheet
Backend
Node.jsExpress.jsPythonFastAPI
003Spec_Sheet
Databases
MongoDBCosmos DB
004Spec_Sheet
Cloud/DevOps
AWSAzureJenkinsNginxBicepLinuxCI/CD Pipelines
005Spec_Sheet
AI/ML
Agentic AILangChainHuggingFaceMCPGenAIOpenAIGeminiAzure AIClaudeRAG/RAG 2.0/Agentic Rag/Graph Rag
006Spec_Sheet
Tools
GitPostmanVS CodeCursorWindsurfAntigravityClaude CodeGitHub CopilotCodexExcelPowerPointWord
007Spec_Sheet
Other
REST APIsJWTWebSocketsJSON
PR
Featured Projects
NO.03
Selected Works
(27 Projects)
Full Stack#04
GENIE
GENIE is a modern, full-stack template designed for building AI agents using LangGraph.js on the frontend and Model Context Protocol (MCP) on the backend. It combines a high-performance Next.js 15 client with a flexible Python server, offering a robust foundation for intelligent applications.
Next.jsMongoDBPythonGeminiAgentic AIlangchainLangGraph.jsMCP
AI/ML#05
SPARC (Syntax & Programmatic Assistance Resource Component)
SPARC (Syntax & Programmatic Assistance Resource Component) is a command-line chat application that acts as an AI/ML coding assistant. It leverages the power of Google's Gemini Pro model to understand and respond to your coding-related queries. SPARC can interact with your file system, read and write files, execute code, and even generate diagrams to provide a seamless and efficient development experience.
PythonGeminiBashAgent
Work History
NO.04
Experience
5.4YRS XP
Aug 2024 – Present
KellyOCG
GenAI Full Stack Developer
GRACE Boost - AI-powered browser extension
Azure, Azure AD, OpenAI, Typescript, Node.js, Cosmos DB, Preact, ESBuild
- Architected a production AI browser extension (Manifest V3) with a domain-aware injection system using deduplication guards and a server-driven dynamic configuration API for zero-redeployment logic updates.
- Engineered an AI agent system using Azure OpenAI function calling to power specialized recruiter tools — summary generation, editing, ATS-optimized resume writing, and branded job postings with 7 templates.
- Built a dual-mode AI chatbot featuring a general assistant and a Bullhorn-specialized recruiter agent with tool use, multi-turn parameter collection, and structured JSON formatting for UI rendering.
- Developed an intelligent page parsing and reinjection engine that extracts form data from nested Bullhorn iframes and simulates full user interaction events (mousedown, input, blur) to write AI-generated content.
- Created a generic page analyzer that programmatically scans host forms to classify Novo UI components (pickers, chips, editors), producing structured snapshots for context-aware AI processing.
- Built a multimodal pipeline supporting PDF, DOCX, XLSX, and images via Azure Document Intelligence with Worker Thread fallback; implemented secure Multer storage with automatic temp file cleanup.
- Implemented secure Azure AD OAuth 2.0 with RS256 JWT validation, automatic token refresh on 401s, and server-side JWKS caching with exponential backoff retry logic for high availability.
- Designed a Cosmos DB layer across 4 containers for chat history and telemetry; implemented Zustand-based state management with dual access patterns for cross-context sharing between scripts and Preact components.
- Integrated Databricks SQL for AI-ranked candidate retrieval and built a Shadow DOM-isolated, draggable floating UI with click-vs-drag detection and context-aware menus to prevent CSS collisions.
- Developed a comprehensive telemetry system capturing token usage and tool traces for PowerBI dashboards, alongside a network diagnostics endpoint and React ErrorBoundary components for graceful recovery.
- Optimized bundle size to <300KB using ESBuild tree-shaking and code splitting; established a multi-environment CI/CD pipeline on Azure DevOps with infrastructure provisioning via Bicep/ARM templates.
- Successfully delivered the entire end-to-end extension within 1 month by leveraging AI coding assistants (Claude, Gemini, Codex) to automate the SDLC and complex boilerplate generation.
Project GRACE 2.0 - GenAI Chat Application
Azure, Azure AD, OpenAI, Gemini, Claude, Next.js, Cosmos DB, Bicep, ESLint, MCP, Agentic AI, RAG, LangChain
- Worked on GRACE, an enterprise-grade AI chat platform using Next.js 14, React 18, TypeScript, and Tailwind CSS, deployed on Azure for organization-wide use across Kelly Services.
- Engineered a multi-model AI orchestration layer integrating Azure OpenAI (GPT-4), Anthropic Claude, Google Gemini, and Perplexity APIs, enabling context-aware conversations with configurable persona-based workflows.
- Built a Retrieval-Augmented Generation (RAG) pipeline using Azure AI Search and Azure Blob Storage, enabling users to upload and query documents with AI-powered citation-backed responses.
- Designed and implemented 10+ domain-specific AI agents with custom prompt engineering, file processing, and extension frameworks.
- Developed a full document intelligence pipeline integrating Azure Document Intelligence and Azure Blob Storage for automated document parsing, OCR, and multi-format file processing.
- Implemented enterprise authentication and RBAC using NextAuth with Azure AD, role-based access control, and Azure Key Vault for secrets management across a multi-tenant architecture.
- Built a database migration framework with 40+ versioned migrations on Azure Cosmos DB, ensuring zero-downtime schema evolution for production deployments.
- Integrated multimodal capabilities including DALL-E image generation, GPT-4 Vision for image analysis, and Azure Speech Services for text-to-speech/speech-to-text functionality.
- Developed a reporting and analytics dashboard with usage tracking, conversation logging, and admin tooling for monitoring platform adoption and AI model performance.
- Achieved full Veracode compliance by leveraging Claude for deep security inspections and automated remediation of high-severity vulnerabilities, while leading monthly security updates based on penetration test feedback.
- Optimized mobile experience with dynamic textbox resizing (95% user satisfaction) and implemented prompt library functionality for custom prompt management.
- Introduced AI agent capabilities with LangChain and MCP (HTTP) integration for advanced tool-use and automation.
- Engineered a self-healing UI automation workflow using browser-use AI library to validate complex GRACE interface features, ensuring regression-free deployments of dynamic AI components.
Apr 2023 – Jun 2024
Poumki Digital LLP
Full Stack Developer
Project Convergence - Data Analytics Platform
MERN Stack, AWS, Jenkins, Nexus, Linux, Nginx
- Architected a scalable CI/CD infrastructure using self-hosted Jenkins runners on AWS EC2, integrating Nexus and S3 to reduce artifact storage costs by 30%.
- Engineered a robust rollback pipeline system, significantly improving deployment reliability and minimizing production downtime.
- Implemented high-concurrency real-time features using Socket.IO and developed JWT-authenticated REST APIs with 100% unit test coverage.
- Automated disaster recovery by developing AWS Lambda-based MongoDB backup scripts, ensuring data integrity and high availability.
- Enabled full observability with Winston and LogLevel logging for production monitoring.
- Implemented optimized pagination and search filters on the frontend to enhance data accessibility for large analytics datasets.
Project e-slide - Presentation Sharing Platform
React, SASS, DynamoDB, AWS Lambda, Amplify, GraphQL, PostgreSQL
- Architected a highly scalable presentation rendering engine using React and GraphQL, supporting multi-format document uploads and real-time state synchronization.
- Implemented a serverless backend architecture using AWS Amplify and Lambda, optimizing for global availability and reduced operational overhead.
- Developed a granular user moderation system with complex access control logic and PostgreSQL-based persistence to ensure community safety.
- Optimized asset delivery and frontend performance, achieving a 40% reduction in slide load times for international users via CloudFront/S3.
- Added comprehensive multilingual support using React-i18next for a global audience.
Project Izycourse - Online Course Platform
React, SASS
- Engineered a responsive e-learning platform featuring advanced progress tracking, interactive course modules, and seamless student enrollment workflows.
- Optimized UI/UX performance and accessibility, resulting in a 25% increase in mobile engagement and achieving full WCAG compliance.
- Implemented comprehensive multilingual support using React-i18next, enabling a localized experience for a global student base.
Mar 2021 – Apr 2023
Tata Consultancy Services (TCS)
Full Stack Developer - Rapid Labs
AI/ML Prototypes for Healthcare
AngularJS, Python, Django, Vue.js, Flask
- Spearheaded the development of healthcare-focused AI prototypes, including a NLP-driven ticket classification system (85% accuracy) and a computer vision model for ulcer detection (92% precision).
- Engineered full-stack pilot applications using Django and Vue.js/AngularJS to demonstrate AI model feasibility and clinical value to stakeholders.
- Managed the end-to-end ML lifecycle for research prototypes, from data preprocessing and augmentation to model deployment and UI integration.
Jan 2020 – Mar 2021
Tata Consultancy Services (TCS)
Site Reliability Engineer
SRE Automation Tools
.NET, MySQL, C#
- Engineered the 'Core Analysis Tool' in C#/.NET, reducing ServiceNow ticket resolution time by 50% (2x faster) through automated root cause analysis.
- Developed the 'Akamai Report Generator' and 'Auto Delegation Tool' to automate complex data validation, saving 500+ manual work hours annually.
- Optimized system monitoring and incident response pipelines, significantly reducing MTTR for critical production environments.
Academic Background
NO.05
Education
Oct 2025 – Current
Master of Computer Applications (MCA) - AI/ML
Amrita Vishwa Vidyapeetham
Jul 2017 – Sep 2020
Bachelor of Computer Applications (BCA)
VLB Janakiammal College of Arts and Science, Coimbatore