Skip to content
View RisAhamed's full-sized avatar
🎯
Working Onvertime to learn and Develop
🎯
Working Onvertime to learn and Develop
  • chennai
  • 01:52 (UTC -12:00)

Highlights

  • Pro

Block or report RisAhamed

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
RisAhamed/README.md
Typing SVG

🧠 Who Am I?

I'm an AI/LLM Engineer who builds systems that don't just respond β€” they reason, plan, and act.

My focus: Agentic AI β€” multi-agent systems using LangGraph and LangChain where autonomous agents collaborate, use tools, and solve real-world tasks end-to-end.

I just graduated in 2026 with a B.Tech in AI & Data Science (CGPA 8.37). Everything I know came from building things, breaking them, and shipping them.

riswan = {
    "focus"      : ["Agentic AI Systems", "LLM Fine-Tuning", "RAG Pipelines"],
    "stack"      : ["LangGraph", "LangChain", "LlamaIndex", "HuggingFace", "Groq"],
    "deployment" : ["Docker", "AWS EC2/ECR", "FastAPI", "GitHub Actions"],
    "currently"  : "Building multi-agent systems that work while I sleep πŸ€–",
    "fun_fact"   : "I love Docker more than most people love coffee β˜•"
}

⚑ What I Build

System What It Does Stack
πŸ₯ Agentic Medical AI Multi-agent RAG over medical datasets with context-aware reasoning LangGraph Β· Pinecone Β· Groq Β· Docker Β· AWS
πŸ” Autonomous Research Agent Researcher + Analyst + Writer agents that produce full reports LangGraph Β· Tavily Β· Groq Β· Streamlit
πŸš— MLOps Vision Pipeline End-to-end YOLOv7 pipeline: ingest β†’ train β†’ evaluate β†’ deploy MongoDB Β· AWS S3/EC2 Β· MLflow Β· GitHub Actions
πŸ€– LLM Fine-Tuning Domain-adapted LLMs using LoRA & QLoRA Unsloth Β· HuggingFace Β· Weights & Biases

πŸ”§ My Agentic Stack

Core AI & LLM

Python PyTorch TensorFlow HuggingFace

Agentic & LLM Orchestration

LangChain LangGraph LlamaIndex Groq

Vector Databases & Retrieval

Pinecone FAISS

MLOps & Deployment

Docker AWS GitHub Actions MLflow

Data & Infra

MongoDB FastAPI Linux Azure


πŸ“Š GitHub Stats

stats graph languages graph
streak stats

🧩 How My Agent Systems Work

User Input
    β”‚
    β–Ό
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚         Supervisor Agent            β”‚  ← LangGraph orchestrator
β”‚  (Plans tasks, routes to agents)    β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                 β”‚
    β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
    β–Ό            β–Ό             β–Ό
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚Researchβ”‚  β”‚Analyst β”‚  β”‚ Writer   β”‚
β”‚ Agent  β”‚  β”‚ Agent  β”‚  β”‚  Agent   β”‚
β”‚(Tools) β”‚  β”‚(Python)β”‚  β”‚(LLM out) β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β””β”€β”€β”€β”€β”€β”€β”€β”€β”˜  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
    β”‚            β”‚             β”‚
    β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                 β”‚
                 β–Ό
         Final Output βœ…
   (Report / API Response / Action)

🎯 Current Focus

  • πŸ” Cyclic LangGraph agents β€” agents that retry, self-correct, and loop until success
  • 🧠 Long-term agent memory β€” persistent state across sessions
  • βš™οΈ LLM fine-tuning on domain data β€” LoRA + QLoRA with Unsloth
  • πŸš€ Deploying agentic systems as APIs β€” FastAPI + Docker + AWS

🀝 Connect With Me

LinkedIn Gmail HuggingFace


"Don't build AI tools. Build AI systems that build tools."

Visitor Count

Pinned Loading

  1. ANPR ANPR Public

    This project is an Automatic Number Plate Recognition (ANPR) application that can detect and extract license plate numbers from images or videos.

    Jupyter Notebook

  2. ML-pipeline-using-DVC-AWS ML-pipeline-using-DVC-AWS Public

    This is Exercise For implementing Dvc and getting practive with MLOPS operations

    Jupyter Notebook

  3. Vehicle-Insurance-Prediction Vehicle-Insurance-Prediction Public

    This project implements an end-to-end MLOps pipeline for predicting whether a customer would be interested in vehicle insurance. The pipeline includes data ingestion from MongoDB, data validation, …

    Jupyter Notebook

  4. MLOPS-project-AWS-K8s-Dashgub MLOPS-project-AWS-K8s-Dashgub Public

    Python

  5. Personal-Research-Assistant Personal-Research-Assistant Public

    Python 1