Suchith Koduru

AI engineer. I build LLM agents and the systems around them.

Currently at 10xscale.ai, building multi-agent systems and memory architectures. Previously research intern at IIT Delhi. B.Tech CS, IIT Delhi 2025.

About

I'm an AI Software Engineer at 10xscale.ai, where I build multi-agent systems using LangChain, LangGraph, and FastMCP. I've contributed to the open-source agent framework Agentflow — PRs #17 and #19 merged — and built an MCP server for PostgreSQL that lets agents query structured data with natural language.

I design persistent memory systems using Qdrant and Mem0 for long-horizon reasoning, and prototyped a Raspberry Pi robot with real-time AI responses for live demos. Before this, I was a research intern at IIT Delhi where I built a Maternal Health Risk Predictor — benchmarking SVM, Random Forest, XGBoost, and Gradient Boosting to reach 99% accuracy.

Now

Shipping multi-agent pipelines at 10xscale.ai
Contributing to Agentflow, building on FastMCP
Building MCP tools for PostgreSQL agent integration

Projects

Deep Research Agent

Autonomous web research agent built for the HuggingFace MCP Hackathon. Researches topics, synthesizes sources, and writes comprehensive answers.

Python
MCP
LangChain
HuggingFace

Agentflow

Contributed to this open-source AI agent framework. Work focused on code structure and unit test coverage.

↗ PR #17 ↗ PR #18 ↗ PR #19

Python
LangChain
Unit Testing

Customer Churn Prediction

End-to-end ML pipeline for telecom churn using Random Forest with SMOTE, SHAP interpretability, and threshold optimization.

Python
Scikit-learn
SHAP

Background

I work primarily with Python, LangChain, LangGraph, PyTorch, and PostgreSQL. I deploy with Docker on Linux and have experience with C++, Flask, JavaScript, Qdrant, FastMCP, and Scikit-learn.

B.Tech in Computer Science, Indian Institute of Technology Delhi (2021–2025).

JEE Advanced 2021: AIR 479 · JEE Mains 2021: AIR 620 · TS-EAMCET 2021: Rank 201