• Senior AI Platform Engineer with 20+ years of experience designing and delivering scalable cloud-native and AI-powered systems across global environments. Specialized in production-grade LLM and RAG architectures using LangChain, LangGraph, FastAPI, and hybrid graph?vector retrieval (Neo4j, Pinecone, Weaviate, Qdrant).
• Architect of multi-agent AI workflows, deterministic RAG pipelines with schema validation, and observability-first LLM platforms designed for reliability, cost control, and scalable deployment. Experienced across AWS, GCP, and Azure, with strong expertise in CI/CD, Kubernetes, and cloud-native deployment, along with applied knowledge of MLOps concepts using Vertex AI and SageMaker.
• Combines deep backend engineering expertise with practical generative AI implementation to build secure, high-performance, and production-ready AI systems.

Technical Skills

Frontend:

• ReactJS
• Redux
• JavaScript
• Node.js (Express)
• HTML
• CSS
• SCSS

UI Frameworks:

• Material UI
• Carbon Components
• Ant Design
• Tailwind CSS
• Bootstrap

Backend & APIs:

• Python
• Django
• Flask
• FastAPI
• DRF
• GraphQL
• Apollo
• Postman
• Swagger
• SoapUI

Cloud/DevOps:

• AWS
• Azure
• GCP Cloud Run
• Docker
• Kubernetes
• Terraform
• Git
• SVN
• TFS
• CI/CD pipelines

AI/ML & Generative AI:

• LangChain
• LangGraph
• RAG (Retrieval-Augmented Generation)
• OpenAI API
• TensorFlow.js
• Vector Databases
• Pandas
• Neo4j Graph Workflows

Testing:

• Pytest
• PyUnit
• Jest
• Mocha/Chai
• xUnit/NUnit

Monitoring:

• Grafana
• OpenTelemetry
• DataDog

Professional background:

10/2024 ? 06/2025:
Place of Work: Germany
Role: Senior Fullstack Developer
Customer: Debitos

Tasks:

• Architected multi-screen data workflow with Nextjs/ React/ TS, boosting mapping speed by 50%
• Refactored backend into FastAPI + SQLAlchemy, reducing memory use by 45%
• Integrated LangChain & LangGraph workflows with Pinecone vector DB to enable semiautomated data mapping and LLM-powered search
• Built RAG-powered workflows integrating LangChain + Pinecone, enabling LLM-augmented data search
• Containerized backend services (FastAPI/Node.js) and React/TypeScript frontend, aligning with production-ready architecture and CI/CD pipelines

12/2022 ? 07/2024:
Place of Work: Germany
Role: Senior Fullstack Developer
Customer: Breakwater Solutions

Tasks:

• Built ReactJS components with AWS Cognito & S3, increasing engagement 15%
• Optimized GraphQL with DataLoader, improving performance by 35%
• Integrated RabbitMQ + FastAPI for async workflows; scaled submissions 35

02/2016 ? 08/2022:
Place of Work: India 
Role: Project Lead
Customer: Persistent Systems

Tasks:

• Enhanced React/Redux UI performance by 35% via lazy loading and code-splitting
• Built Django REST APIs with Redis caching, cutting response times 60%
• Refactored PostgreSQL queries; reduced API latency from 5 mins to under 2 mins

10/2007 ? 01/2016:
Place of Work: India 
Role: Senior System Analyst 
Customer: Atos

Tasks:

• Developed scalable Django/Flask APIs, boosting backend performance 30%
• Migrated data pipelines to Azure Data Factory, reducing ETL time 40%
• Deployed containerized services with Docker/Kubernetes for isolation

02/2007 ? 06/2007:
Place of Work: India 
Role: System Analyst 
Customer: Deloitte

12/2001 ? 11/2004:
Place of Work: India 
Role: Technical Consultant 
Customer: Systime Pvt Ltd

10/2000 ? 10/2001:
Place of Work: India 
Role: Junior Software Engineer
Customer: Silicon Interfaces