Nitish

Class Location

Online class via Zoom

Student's Home

Tutor's Home

Years of Experience in HTML Training

6

Class Location

Online class via Zoom

Student's Home

Tutor's Home

Years of Experience in Generative AI Classes

14

Teaching Experience in detail in Generative AI Classes

I teach Generative AI and Agentic AI development to live student cohorts through hands-on, code-first sessions. My teaching focuses on helping learners move beyond theory into building real systems using modern LLM tooling. My instruction covers the end-to-end lifecycle of GenAI application development, including: Python Foundations Foundations of Large Language Models (LLMs) Prompt engineering and structured prompting Retrieval-Augmented Generation (RAG) system design Vector databases such as ChromaDB and Qdrant Agentic workflows using LangGraph and tool-calling architectures Guardrails, input validation, and prompt-injection protection Fine-tuning concepts and evaluation strategies Building production-ready APIs using FastAPI and Python I teach these topics through live coding sessions, architectural walkthroughs, and project-based learning, where students build working systems such as: Document-question-answering systems using RAG Multi-step AI agents with memory and tools Domain-specific chatbots LLM pipelines with evaluation loops My teaching style emphasizes: Breaking down complex GenAI concepts into simple mental models Explaining tradeoffs between RAG, fine-tuning, and prompting Encouraging students to think in terms of systems design, not just model usage Helping learners debug LLM behaviour and understand failure modes The goal of my teaching is to enable students to design, build, and deploy agentic AI systems confidently in real-world applications, rather than only learning theory.

Class Location

Online class via Zoom

Student's Home

Tutor's Home

Years of Experience in Data Science Classes

14

Teaching Experience in detail in Data Science Classes

I teach Data Science and Machine Learning through live, hands-on sessions focused on building strong fundamentals and practical problem-solving skills using Python. My teaching covers the complete data science workflow, including: Data analysis using NumPy and Pandas Data visualization using Matplotlib and Seaborn Exploratory Data Analysis (EDA) Feature engineering and preprocessing Supervised and unsupervised learning using scikit-learn Model evaluation and validation techniques Bias-variance tradeoff and overfitting control End-to-end ML pipeline development I also teach core statistical concepts required for Data Science, such as: Probability fundamentals Distributions and sampling Hypothesis testing Regression fundamentals Evaluation metrics (precision, recall, F1, ROC-AUC) Sessions are conducted using live coding, dataset-driven exercises, and real-world problem scenarios, where students build projects such as: Predictive models using regression and classification Customer segmentation using clustering Data cleaning and transformation pipelines Model comparison and evaluation workflows My teaching approach emphasizes: Building strong intuition behind algorithms rather than memorization Explaining the mathematics behind ML models in a practical way Teaching students how to debug models and interpret results Developing the ability to move from raw data to deployable ML solutions The objective of my teaching is to help students become confident in analyzing data, building machine learning models, and making data-driven decisions using Python-based tools.