Skip to content
View Nandini-Inuguru's full-sized avatar
1 follower · 2 following

Block or report Nandini-Inuguru

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Nandini-Inuguru/README.md

Hi, I'm Nandini 👋

Building distributed systems, agentic AI pipelines, and low-level tools from scratch

Portfolio LinkedIn Email

🧭 About Me

  • 🎓 B.Tech in Computer Science, PES University, Bengaluru (2023 – 2027)
  • 💻 SDE Intern @ Fiserv, ex AI/ML Intern @ Bluedrop AI
  • 🛠️ I like building things at the systems level — container runtimes, distributed pipelines, agentic RAG — and understanding why they work, not just calling the API
  • 🌱 Currently exploring multimodal LLMs and agentic system design
  • 📫 Reach me at nandiniinuguru2006@gmail.com

🚀 Featured Projects

🐳 Docksmith Docker-like container build & runtime system built from scratch in Go using raw Linux syscalls — no Docker, runc, or containerd.

  • ⚡ 92% faster rebuilds via SHA-256 content-addressed caching
  • 🔒 Full filesystem isolation using namespaces + chroot Go Linux Syscalls Namespaces Content-Addressed Storage

📊 LogScale Distributed real-time log analytics platform with a 7-microservice ingestion pipeline behind gRPC.

  • ⚡ Query latency cut ~99% (800ms → 5ms)
  • 🔥 Sustains ~5,000 events/sec with sharded PostgreSQL + Kafka Java Spring Boot Kafka Redis gRPC React

🤖 Self-Healing Agentic RAG Agentic RAG pipeline with a task-planning agent and a self-monitoring correction loop.

  • 📉 90% fewer hallucinations vs. an uncorrected baseline
  • 🎯 87.2% accuracy on HotpotQA / RAGBench LangChain FAISS BM25 Gemini Groq OpenAI

🛍️ CoMemo++ Multimodal trend-forecasting LVLM for e-commerce, fusing images, reviews, and sales signals.

  • 📦 22M+ Amazon reviews, 5.8M+ products processed
  • 🧠 200K+ ViT/CLIP embeddings indexed in ChromaDB CLIP ViT RoPE-DHR DuckDB ChromaDB

🌍 Open Source

🧰 Tech Stack

Languages Python Java C++ JavaScript SQL Go

ML / AI PyTorch TensorFlow Scikit-learn Pandas Hugging Face

Backend & Systems Spring Boot Flask Kafka Redis PostgreSQL gRPC React Docker AWS Git

📊 GitHub Stats

Thanks for stopping by — always happy to talk systems, ML, or open source 🚀

Popular repositories Loading

  1. IO_Project IO_Project Public

    Jupyter Notebook

  2. Sales-forecasting Sales-forecasting Public

    Python

  3. yolo-road-detector yolo-road-detector Public

    JavaScript

  4. my_calci my_calci Public

    A simple CLI based Calculator

  5. my-calci my-calci Public

    A simple CLI based Calculator

    Python

  6. nba-mvp-prediction nba-mvp-prediction Public

    NBA MVP Prediction using Naive Bayes & Logistic Regression (CS229 project)

    Jupyter Notebook