ML/AgenticAI Coding Interview

Master core machine learning coding rounds by building fundamental ML algorithms and neural network architectures from scratch using clean, modular Python.

Many ML interview loops test your ability to implement algorithms without relying on high-level packages like Scikit-Learn or PyTorch wrapper functions. Leveraging a backend SDE background, these sessions help you combine software engineering best practices with core ML math to write production-quality code under interview conditions.

What we will cover:

• Classical ML Algorithms from Scratch: Hands-on practice implementing Linear/Logistic Regression, Decision Trees, Random forest, K-Means Clustering, KNN, and Naive Bayes, Bagging, Boosting trees Neural Networks etc, using pure Python and NumPy.
• Agentic AI coding from scratch: Hands-on practice implementing agentic-AI pattern for a specific use case.
• Realistic Mock Interview (Optional): A live 45-minute coding session using standard ML interview problems, followed by 15 minutes of structured feedback on code modularity, edge-case handling, and algorithmic communication.

Who this session is for: Software Engineers, college students, and aspiring ML practitioners preparing for ML coding rounds who want to confidently implement classical ML models and basic neural networks from the ground up.

Bring 1–2 specific problems or topics you want to target, or let me curate a set based on your goal!