Headline

Building production AI systems · LangGraph Agents · RAG Pipelines · Voice AI · Open to AI Eng roles

About

I build AI systems that don't just demo well — they work in production. Currently at TCS as a Full Stack Developer, but my real obsession is AI engineering. I've built a stateful agentic RAG system with LangGraph handling multi-hop health insurance queries — combining vector search, BM25, a knowledge graph of 10K+ edges, and semantic caching to get sub-millisecond response times. I've also built FlowTalk, a real-time voice AI with a full STT → LLM → TTS pipeline running over WebSockets with under-the-hood concurrency in Go. On the backend, I work across .NET, Go, Python and have shipped things like ETL pipelines into Amazon Redshift, Redis caching layers, and RabbitMQ-based microservices at scale. What I'm looking for: AI Engineer or Backend-heavy AI roles at product startups where I can own systems end-to-end — not just integrate APIs, but architect and ship the full thing. If you're building something interesting in AI/healthtech/infra — let's talk. manthenanagendra@gmail.com

Location

Bhimavaram

Work experience

Full Stack Developer at Tata Consultancy Services, Aug 2024 - Present · 2 yrs, Hyderabad, Telangana, India

Full Stack Engineer at Tata Consultancy Services, Aug 2024 - Present · 2 yrs, Engineered an Agentic Retrieval-Augmented Generation (RAG) pipeline using LangGraph and FastAPI to automate application lifecycle management and data quality resolutions for the GEAR team, replacing manual human-in-the-loop workflows. Extracted, parsed, and vectorized enterprise data from 5,000+ ServiceNow requests and 120+ Confluence pages using Docling and ChromaDB to build a centralized semantic knowledge base. Automated query resolutions for internal application service owners, reducing overall manual IT support ticket flow by 60%. Designed and deployed REST APIs in C#/.NET 8 on AWS EC2, serving enterprise-scale workloads; introduced Redis caching to reduce average response latency by ∼40%. Diagnosed OLTP query bottlenecks by designing an ETL pipeline to incrementally sync ServiceNow data into a columnar data warehouse, cutting dashboard query time by ∼60%. Integrated RabbitMQ for asynchronous inter-service messaging, decoupling 3+ microservices and improving fault tolerance.

Education

1, Electronics and communication engineering, National Institute of Technology, Andhra Pradesh

Bachelor of Technology, Electrical, Electronics and Communications Engineering, National Institute of Technology, Andhra Pradesh