Since December 2024 I've been building an AI knowledge platform for a European industrial client at a German software company. Most of my week goes into multi-tenant RAG pipelines on Weaviate and LangGraph multi-agent workflows, plus the Angular, Vue.js and NestJS app they live in.

Before that I freelanced for two years on the MERN stack, shipping e-commerce platforms and event-driven microservices on AWS with Docker, Kubernetes and RabbitMQ. I still own features end to end, from the database schema to the Kubernetes deploy.

Open to Full-Stack / AI Engineer roles. Based in Thiruvananthapuram, Kerala, India, and open to remote work.

Multi-agent service that tailors a resume to a job description without fabricating experience, using a Google ADK pipeline (parallel + sequential agents, schema-enforced outputs) behind a FastAPI service with a PDF-upload web UI.
Python · Google ADK · Multi-Agent · FastAPI · Gemini · Pydantic

Multi-agent system that turns a single question into a researched report: four cooperating agents (Supervisor, Researcher, Writer, Reviewer) as nodes in a stateful StateGraph, with dynamic LLM-based routing, an iterative Writer–Reviewer refinement loop, and a provider-agnostic LLM layer (Groq, Gemini, OpenAI, Anthropic).
Python · LangGraph · LangChain · Pydantic v2 · Docker

Production-style RAG chatbot grounded in user PDFs (including scanned/image-only PDFs via Tesseract OCR), with visual, verifiable citations mapping each retrieved chunk back to bounding boxes on the source page. Semantic retrieval via Sentence-Transformers + FAISS with a TF-IDF fallback.
Python · LangChain · FAISS · Tesseract OCR · PyMuPDF · Streamlit

Full-Stack AI Engineer · German AI company (industrial software) · Dec 2024 – Present
Building an AI-powered industrial knowledge platform on Angular, Vue.js & NestJS: document ingestion with hierarchical chunking, multi-tenant Weaviate semantic search, and LangGraph multi-agent workflows with a decorator-based plugin system for tool discovery and LLM-as-router sub-agents.

MERN Developer · Freelance / Self-Employed · Nov 2022 – Nov 2024
Shipped e-commerce platforms and event-driven microservices (Docker, Kubernetes, RabbitMQ) on AWS; cut API latency ~60% with Redis caching and Bull job processing.

• Frameworks & orchestration: LangChain · LangGraph · Multi-Agent Orchestration · Agentic AI · Model Context Protocol (MCP)
• Retrieval & search: RAG Pipelines · Vector Embeddings · Semantic Search · Weaviate (Vector DB)
• Models & tooling: OpenAI API · Anthropic Claude API · Prompt Engineering · SSE Streaming · Langfuse (Observability)

Stats, contribution calendar and coding time (updated daily by GitHub Actions)

GitHub Stats

Contribution Calendar

Activity

📊 This Week I Spent My Time On

🕑︎ Time Zone: Asia/Kolkata

💬 Programming Languages: 
Markdown                 3 hrs 26 mins       ████████████░░░░░░░░░░░░░   46.02 % 
Other                    1 hr 42 mins        ██████░░░░░░░░░░░░░░░░░░░   22.83 % 
JSON                     1 hr 21 mins        █████░░░░░░░░░░░░░░░░░░░░   18.12 % 
TOML                     26 mins             █░░░░░░░░░░░░░░░░░░░░░░░░   05.81 % 
Text                     14 mins             █░░░░░░░░░░░░░░░░░░░░░░░░   03.19 % 

🔥 Editors: 
Claude Code              7 hrs 28 mins       █████████████████████████   99.99 % 
VS Code                  0 secs              ░░░░░░░░░░░░░░░░░░░░░░░░░   00.01 % 

Last Updated on 12/11/2026 00:56:12 UTC