Thanks to visit codestin.com
Credit goes to Github.com

Skip to content
View SRafi007's full-sized avatar
🏠
Working from home
🏠
Working from home
2 followers · 4 following

Achievements

Achievement: Pull SharkAchievement: Quickdraw

Achievements

Achievement: Pull SharkAchievement: Quickdraw

Block or report SRafi007

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
SRafi007/README.md

Hi, I'm Rafi 👋

AI Developer • ML Engineer • Full-Stack Builder

Passionate about intelligent systems, LLM applications, multi-agent workflows, and scalable AI products.
I build practical AI tools — from RAG chatbots to CV ranking systems — combining machine learning with real engineering.

🌐 Portfolio: sadmansakibrafi.vercel.app
📩 Email: [email protected]

🚀 What I Work On

  • LLM-based systems (Gemini, LLaMA, Qwen, Mistral)
  • Multi-agent workflows (CrewAI, custom agent frameworks)
  • RAG pipelines (Qdrant, Pinecone, FAISS)
  • AI-driven platforms for automation, ranking, and analysis
  • Full-stack engineering with FastAPI, Next.js, and NestJS
  • Local + cloud AI infrastructure (Ollama, Docker)

🧠 Core Skills & Tools

AI / ML

Ollama

Frameworks & Databases

Full-Stack Development

🛠 Featured Projects

🔹 Phone Query Review System

LLM-powered phone specification retrieval + contextual review generator using RAG and multi-agent logic.

🔹 IntelliHire AI — CV Ranking System

Ranks resumes using hybrid AI pipelines, embeddings, and explainable scoring (Qdrant + Qwen 2.5 7B).

🔹 MyCaptionAI

Generates contextual social media captions through an AI-driven API service.

🔹 AI Tutorial Crew

A multi-agent learning assistant using CrewAI + local LLMs (Ollama-Mistral).

🔹 Jervis — AI Assistant

Context-aware multi-agent personal assistant using FAISS + Qwen/Mistral.

🌍 Connect With Me

languages graph

Pinned Loading

  1. E--Governance-Project-With-Nestjs E--Governance-Project-With-Nestjs Public

    TypeScript

  2. 2-layer-neural-network-from-scratch-using-NumPy 2-layer-neural-network-from-scratch-using-NumPy Public

    2-layer neural network from scratch using NumPy

    Jupyter Notebook

  3. ai-tutorial-crew ai-tutorial-crew Public

    Multi-agent AI system using CrewAI and Ollama to automatically research, write, and review beginner-friendly Python tutorials

    Python 3

  4. CartPole-RL-The-Classic-RL-Hello-World CartPole-RL-The-Classic-RL-Hello-World Public

    CartPole Balancing (Classic Control Problem) - Beginner-Level Reinforcement Learning Project Ideas for

    Python

  5. Optimize-The-Pandas-Dataframe-Memory-ML Optimize-The-Pandas-Dataframe-Memory-ML Public

    Optimize The Pandas Dataframe Memory | ML

    Jupyter Notebook

  6. Samsung-Phone-Query-Review-System Samsung-Phone-Query-Review-System Public

    An intelligent multi-agent system with LLM-powered chatbot, web scraping, and FastAPI backend to query, compare, and review Samsung smartphones.

    Python