Available for AI Systems & Software Engineering

Hi, I'm Samar Nathani 👋

AI Systems & Applied ML Engineer building intelligent systems, scalable pipelines & agentic infrastructure

Python · LangGraph · Deep Learning · IIT Madras (Rank 2 / 800+) · Open Source Contributor

Rank 2 / 800+ IITM DL & GenAI Best Project
7+ Merged Global Open Source PRs
0.924 LB 1.7M Amazon ML Challenge
985 Episodes Sequential Matching Solver

About

I build production AI systems and scalable software that turn complex, high-dimensional problems into reliable results — from autonomous agents and combinatorial research algorithms to multi-model RAG pipelines and developer tooling.

Pursuing a B.Sc. in Programming and Data Science at IIT Madras, where I secured Rank 2 out of 800+ students in the Best Course Project Competition for Deep Learning & Generative AI (MAP@3: 0.76724) and serve as Team Lead orchestrating AI sprint workflows for a 6-developer team.

Active contributor to global open source with merged pull requests into pytorch, supabase, faststream, and django-modern-rest. Awarded Hacktoberfest 2026 Completionist++.

Languages

  • Python
  • Java
  • SQL
  • JavaScript
  • HTML/CSS

AI / ML & Retrieval

  • RAG & Vector Search
  • LangGraph / LangChain
  • PyTorch & Transformers
  • FAISS & pgvector
  • LightGBM & XGBoost

Backend & Tooling

  • Model Context Protocol (MCP)
  • FastAPI & Flask
  • JSON-RPC 2.0 Stdio
  • Vue 3 & Vite
  • Ollama & Local LLMs

DevOps & Engineering

  • Git & GitHub Actions (CI)
  • Docker Containers
  • Pytest (Hermetic Mocking)
  • AST Parsing & Slicing
  • Supabase & SQLite

Projects

Context Optimization MCP

opencode-context-mcp

Zero-dependency Model Context Protocol (MCP) server cutting prompt token burn by 75%–90% via AST skeleton slicing with line anchors [L45-88], terminal noise filtering, and test reducers.

AI/MLPythonMCPAST
View Repository
985 Episodes Evaluated

The-Sequential-Matching-Problem

24-track agentic research programme; screened 30 candidate methods over 985 episodes with a polynomial-time exact-k Edmonds' blossom maximum-weight matching solver.

AI/MLPythonAlgorithmsSimulation
View Repository
🥈 Rank 2 / 800+ (MAP@3: 0.767)

smart-mcq-solver

Rank 2 out of 800+ students at IIT Madras. 4-tier ensemble: MCQNet (65K dual n-grams), fine-tuned ELECTRA (5-head MSD & LLRD), MiniLM-L12, and Wikipedia Qwen RAG.

AI/MLPythonRAGPyTorchELECTRA
View Repository
1.7M Records · 0.924 LB

amazon-ml-2026

CPU-only entity resolution pipeline for 1.7M records (Public LB: 0.924). Budget-capped candidate blocking (96.3% recall) feeding a 36-feature GBDT scoring engine with chunk checkpointing.

AI/MLPythonLightGBMXGBoostPolars
View Repository
On-Device Qwen 2.5 7B

devpulse

Local-first Discord bot aggregating tech releases & trending repos; automated multi-item judging using on-device Qwen 2.5 7B via Ollama with zero cloud API cost.

AI/MLPythonLLMOllamaDiscord
View Repository
Full-Stack AI Platform

moodbeats

AI music discovery platform — natural language vibe queries, vector similarity search, neural reranking, and real-time audio feature extraction with Vue 3 frontend.

AI/MLPythonRAGFull-stackVue 3
View Repository
StateGraph + pgvector

ai-research-agent

Autonomous research assistant built on LangGraph (compiled StateGraph), dynamic tool routing, Supabase pgvector dense retrieval, and multi-turn MemorySaver.

AI/MLPythonLangGraphpgvector
View Repository

Open Source

Merged pull requests into global developer infrastructure and open-source ecosystems:

Relevant Coursework

Programming
  • Programming in Python
  • Programming Concepts using Java
  • Programming Data Structures & Algorithms using Python
  • Computational Thinking
Application Development
  • Modern Application Development I & II
  • Database Management Systems
  • Business Data Management
  • Tools in Data Science
Machine Learning & AI
  • Machine Learning Foundations
  • Machine Learning Techniques
  • Machine Learning Practice
  • Introduction to Deep Learning & Generative AI
Mathematics & Statistics
  • Statistics for Data Science I & II
  • Mathematics for Data Science I & II

Get in Touch

Interested in collaborating on AI agent systems, MCP tooling, or competitive ML engineering?