Skip to content
View rasinmuhammed's full-sized avatar
🎯
Focusing
🎯
Focusing
8 followers · 8 following

Achievements

Achievement: Pull SharkAchievement: YOLOAchievement: Starstruck

Achievements

Achievement: Pull SharkAchievement: YOLOAchievement: Starstruck

Block or report rasinmuhammed

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
.github/profile/README.md

Muhammed Rasin O M

Software Engineer · AI/ML & Full-Stack · Kozhikode, India

rasin.io · LinkedIn · rasinbinabdulla@gmail.com

B.Tech CS (Data Science). 1+ year of professional experience spanning data engineering and LLM-powered systems — Databricks, probabilistic entity resolution, RAG architectures, full-stack apps. Currently freelancing and building in public.

Stack: Python · FastAPI · LangChain/LangGraph · SQL · React/Next.js · Docker · GCP · Databricks

Open Source

node-canon - Entity resolution and deduplication for LLM-extracted knowledge graphs. Reconnects fragmented graphs by resolving aliases ("IBM" vs "I.B.M.") offline using graph topology and semantic similarity. No LLM calls needed. pip install nodecanon

misata - Synthetic data engine. Natural language → relational schema → vectorized generation. Supports SQLAlchemy seeding, DB introspection, and streaming at 385k rows/sec. pip install misata · 1,400+ downloads · 55 ★

rag-tui - Terminal debugger for RAG pipelines. Visualize chunking strategies, test retrieval live, export LangChain/LlamaIndex configs. Python API + headless CLI for CI use. pip install rag-tui · 20 ★

In Development

BIM-graph — Agentic RAG over Building Information Models. Neo4j graph retrieval + IFC AST fallbacks to eliminate spatial hallucinations. LangGraph · Groq · Redis semantic caching · Next.js.

Work

  • JMAN Group (Jul 2024–Feb 2025): LLM + web scraping classification pipeline (50% accuracy gain, 80% manual effort cut); Splink/PySpark probabilistic entity resolution on Databricks.
  • DearPriceHunter (Dec 2025–present): Core financial analysis engine for a Swedish logistics startup — OpenAI API integration, full-stack build.
  • Peer reviewer, Network Modeling Analysis in Health Informatics & Bioinformatics (Springer Nature, 2025).

🤝 Let's Connect!

I'm always interested in discussing:

  • 💼 Job Opportunities
  • 🤝 Collaboration - Open-source projects, especially in ML/AI
  • 💡 Technical Discussions - Data engineering, MLOps, full-stack development
  • 🎓 Knowledge Sharing - Best practices, architectural patterns, new technologies

Reach out via:

Profile Views

GitHub Streak

⭐️ From rasinmuhammed

"Continuously refactoring what I know"

Pinned Loading

  1. misata misata Public

    High-performance open-source synthetic data engine. Uses LLMs for schema design and vectorized NumPy for deterministic, scalable generation.

    Python 55 3

  2. rag-tui rag-tui Public

    ⚡ Debug your RAG pipeline without leaving the terminal. Real-time chunking visualization, batch testing, quality metrics, and one-click export to LangChain/LlamaIndex.

    Python 20 4

  3. quantum-generative-art quantum-generative-art Public

    Parametric quantum circuits visualized as interactive cosmic art. Built with Qiskit and p5.js.

    JavaScript

  4. soccer-analysis soccer-analysis Public

    Python

  5. bim-graph bim-graph Public

    A self-healing RAG architecture that cures spatial blindness in gigaproject Digital Twins via deterministic AST traversal

    JavaScript

  6. node-canon node-canon Public

    Entity resolution for LLM knowledge graphs. Merges duplicate nodes created by chunked extraction; "IBM", "I.B.M.", "International Business Machines" → one canonical node. No API key required.

    Python