Turn Your
Winter Break Into
Your Career Break.

Topics covered

• Python syntax, control flow, loops, and core data types
• Functional programming, modular coding, and custom modules
• File handling, exception handling, and error tracing
• Object-Oriented Programming (OOP): Classes, objects, inheritance, and encapsulation
• Working with REST APIs and HTTP requests in Python
• Git & GitHub: Version control, branching, PRs, and repository management

Tools & tech

PythonGitGitHubVS CodeRequestsOSSysJSONCSV

Topics covered

• NumPy arrays, matrix operations, and vectorized computation
• Pandas DataFrames: Indexing, filtering, transforming, and merging
• Handling real-world data issues: Missing values, duplicates, and outliers
• Relational database fundamentals and schema design
• SQL fundamentals: Filtering, grouping, aggregations, and subqueries
• Advanced SQL: Joins, Common Table Expressions (CTEs), and Window Functions

Tools & tech

PythonNumPyPandasPostgreSQLSQLiteDBeaverpgAdminSQLAlchemy

Topics covered

• Exploratory Data Analysis (EDA) pipelines and descriptive statistical metrics
• Data visualization using Matplotlib and Seaborn
• Business KPIs: Customer Lifetime Value (CLV), Churn, ARR, and Conversion Funnels
• Data storytelling principles and executive reporting
• Power BI fundamentals: Power Query, Data Modeling, and DAX formulas
• Designing interactive, multi-page business dashboards

Tools & tech

Power BIDAXPower QueryPythonMatplotlibSeabornJupyter Notebook

Topics covered

• End-to-end Data Science project lifecycle
• Hypothesis testing and inferential statistical analysis
• Feature Engineering: Imputation, encoding categorical variables, and scaling
• Feature selection techniques and handling multicollinearity
• Train-test splitting, data leakage prevention, and cross-validation strategies

Tools & tech

PythonPandasNumPyScikit-LearnSciPyStatsmodelsJupyter Notebook

Topics covered

• Supervised vs. Unsupervised learning paradigms
• Regression algorithms (Linear, Ridge, Lasso) and Classification (Logistic, KNN)
• Tree-based architectures: Decision Trees, Random Forests, and Gradient Boosting (XGBoost)
• Dimensionality reduction (PCA) and clustering algorithms (K-Means)
• Evaluation metrics: Precision, Recall, F1-Score, ROC-AUC, RMSE, and MAE
• Hyperparameter optimization (GridSearchCV, RandomizedSearchCV) and Scikit-Learn Pipelines

Tools & tech

PythonScikit-LearnXGBoostJoblibStreamlitPandasNumPy

Topics covered

• GenAI architecture, foundational models, tokenization, and context windows
• Advanced prompt engineering (Few-Shot, Chain-of-Thought, Directional Stimulus)
• Structured JSON outputs and schema enforcement
• Working with LLM APIs (OpenAI / Anthropic / Open-Source models via Groq/Ollama)
• Text embeddings, vector spaces, and semantic search
• Vector databases (Pinecone, ChromaDB, or FAISS)
• Retrieval-Augmented Generation (RAG): Chunking, retrieval, and synthesis

Tools & tech

PythonLangChainLlamaIndexOpenAI APIGroq APIChromaDBPineconeFAISSHugging FaceStreamlit

Topics covered

• Architecture of AI Agents: LLMs vs. Autonomous Agents
• Planning, reasoning, and reflection loops (ReAct framework)
• Function calling, external tool integration, and web search hooks
• Short-term and long-term memory management
• Multi-agent collaboration frameworks and task delegation
• Human-in-the-loop (HITL) workflows, guardrails, and deterministic fallbacks

Tools & tech

PythonLangGraphCrewAIAutoGenOpenAI APIAnthropic Claude APITavily Search APIRequests

Topics covered

• Engineering an ATS-compliant, impact-oriented resume
• Technical LinkedIn branding and inbound networking strategies
• Professional GitHub repository structuring and technical writing
• Live coding round preparation (Python data structures and SQL window functions)
• Domain interviews: Data Science, Machine Learning, and GenAI system design
• Structured mock interviews and personalized performance feedback
• Target company shortlisting and cold outreach frameworks

Tools & tech

GitHubGitHub PagesVercelMarkdownOverleafLaTeXLoomLinkedIn