Pranjal Bhatt

This isn’t your typical course where you stop at toy datasets like Iris — if you’re serious about mastering GenAI, Machine Learning, LLMs, building real-world AI applications, deploying them locally and on cloud, fine-tuning models, and working with MLOps and AWS services like Lambda and Bedrock, let’s connect.
I will help you with your resume building with actual deployed projects.

GenAI
- LLMs, RAG, LangChain and Agentic AI (multi-agent frameworks)
- Prompt engineering and AI application development
- Vector databases like Chroma and FAISS

Python
- Python basics to advanced for data and AI
- Writing clean and production-ready code
- Libraries: Pandas, NumPy, Scikit-learn

Machine Learning
- End-to-end lifecycle (EDA, feature engineering, model building)
- Model tuning and evaluation
- Advanced algorithms like XGBoost and CatBoost

MLOps
- MLflow for experiment tracking and model management
- CI/CD pipelines using Jenkins
- Model monitoring and production pipelines

AWS
- Deployment using EC2 and S3
- Basics of cloud-based ML deployment
- Scalable architecture understanding

Resume Building
- Resume creation with strong project storytelling
- Portfolio with real-world projects
- Interview preparation for Data Science and AI roles

Industry Projects
- AI based data analyst using multi Agent framework with RAG.
- Document QnA using advanced RAG concepts like Hybrid RAG,Re-Ranking,Agentic RAG
- Comprehensive Industrial level clinical Trails study
- At least 10 Machine learning basic to advance projects from data preparation to model training deployment, model versioning using MLFLOW .
- MLOPS implementation using jenkins,Docker,lambda, bedrock,github actions, Cloudwatch,streamlit for frontend.