I'm an Agentic AI Engineer with 3+ years of experience building autonomous multi-agent systems and scalable RAG architectures. My passion lies in orchestrating stateful LLM workflows using cutting-edge tools like LangGraph and LangChain, backed by a strong foundation in Python, Java/Spring Boot, and robust backend engineering principles.
I specialize in deploying secure, self-correcting AI agents on AWS and Kubernetes that seamlessly handle complex tool-calling and real-time traffic.
Agentic AI & GenAI: LangGraph, LangChain, Model Context Protocol (MCP), RAG Pipelines, LLM Evaluation (Ragas), Tool Calling, OpenAI/Anthropic APIs
Backend & Data: Python (FastAPI, Pydantic), Java (Spring Boot), PostgreSQL (pgvector), Redis, SQL, Vector DBs (Chroma, Pinecone)
Cloud & DevOps: AWS (ECS, Lambda, Bedrock), Docker, Kubernetes (k8s), Terraform, GitHub Actions, CI/CD
- Architected a scalable RAG pipeline for production-grade conversational intelligence.
- Designed a secure Multi-Tenant Architecture on AWS with strict data isolation.
- Developed a high-performance FastAPI orchestration layer utilizing PostgreSQL (pgvector).
- Building advanced Multi-Agent Supervisor Systems with human-in-the-loop workflows.
- Enhancing RAG architecture with hybrid search and continuous LLM evaluation using Ragas.
- Deploying and managing production-grade AI systems on AWS and Kubernetes.
- LinkedIn: Pratik Sontakke
- GitHub: pratiksontakke
- Portfolio: www.pratiksontakke.com
- Email: pratikass488@gmail.com
- YouTube: @PratikSontakkeTech
- X (Twitter): @PratikSontakke_
I'm always open to collaborating on projects at the intersection of Agentic AI, Backend Engineering, and Cloud Infrastructure. Let's build something awesome!