Skip to main content
Back to Programs
🚀Bootcamp

AI Engineering Foundations

From Python to Production AI — 12-Week Bootcamp

Designed for developers, data analysts, and career-changers who want to enter the AI engineering field. You will build real production systems — not just notebooks. Every module has a hands-on lab and a capstone project that goes straight into your portfolio. By week 12 you will have deployed a full ML pipeline and a working RAG-based LLM application on Google Cloud.

Duration

12 weeks

Level

Beginner → Intermediate

Starts

September 1, 2026

Modules

6 modules

Chat on WhatsApp

What You'll Learn

Python, NumPy, Pandas & scikit-learn from scratch
End-to-end ML pipelines: training → evaluation → deployment
CI/CD for ML with GitHub Actions
Experiment tracking: MLflow, DVC, DagsHub
Docker & Kubernetes for ML applications
Vertex AI & GCP for production deployment
LLMOps: RAG chatbot built and deployed as an API
Monitoring with Prometheus & Grafana

Full Curriculum

Detailed Syllabus

01
Weeks 1–2

Python & Data Science Foundations

  • Python: variables, data types, functions, loops, OOP basics
  • NumPy: vectorized operations, broadcasting, array manipulation
  • Pandas: DataFrames, groupby, merge, missing value handling
  • Matplotlib & Seaborn: EDA visualizations and dashboards
  • Lab: Full EDA on a real-world dataset (Kaggle Housing / Titanic)
02
Weeks 3–4

Machine Learning in Practice

  • Supervised learning: linear regression, decision trees, random forests, XGBoost
  • Unsupervised: k-means clustering, PCA dimensionality reduction
  • Model evaluation: cross-validation, ROC-AUC, precision/recall, confusion matrix
  • Feature engineering: scaling, encoding, imputation, feature importance
  • Lab: End-to-end classification project (fraud detection) with scikit-learn
03
Weeks 5–6

MLOps Foundations — Versioning & CI/CD

  • Git branching strategy for ML projects (feature branches, releases)
  • DVC: data versioning, remote storage (GCS/S3), pipeline DAGs
  • MLflow: experiment tracking, parameter logging, model registry
  • DagsHub: unified Git + DVC + MLflow collaboration platform
  • GitHub Actions: automated training, testing, and build pipelines
  • Lab: Reproducible ML pipeline — commit triggers full retrain + eval
04
Weeks 7–8

Containerization & Orchestration

  • Docker: images, containers, multi-stage builds, Docker Compose
  • Containerizing ML inference APIs with FastAPI + Uvicorn
  • Kubernetes: pods, services, deployments, config maps, secrets
  • Helm charts for ML application packaging
  • Apache Airflow: DAG concepts, scheduling, automated retraining pipelines
  • Lab: Containerized ML model served via FastAPI, deployed on Kubernetes
05
Weeks 9–10

Cloud MLOps — Vertex AI & GCP

  • GCP fundamentals: compute, storage (GCS), IAM, service accounts
  • Vertex AI Pipelines: Kubeflow-based ML workflow orchestration
  • Vertex AI Model Registry, Endpoint deployment (online + batch prediction)
  • Feature Store: centralized feature management and serving
  • Cloud Monitoring & logging for ML workloads on GCP
  • Lab: Full MLOps pipeline on Vertex AI — data → train → register → deploy
06
Weeks 11–12

LLMOps & Capstone

  • LLM fundamentals: how transformers work, prompt engineering basics
  • RAG (Retrieval-Augmented Generation): chunking, embedding, vector search
  • LLM evaluation: faithfulness, relevance, hallucination metrics
  • LangChain / LlamaIndex for building LLM applications
  • Deploying LLM APIs on Cloud Run; monitoring with Grafana + Prometheus
  • Capstone: Build and deploy a production RAG chatbot with full CI/CD on GCP

Outcomes

After this program, you'll be able to:

  • Build, evaluate, and deploy end-to-end ML pipelines from scratch
  • Implement CI/CD for ML using GitHub Actions, DVC, and MLflow
  • Containerize and orchestrate ML applications with Docker and Kubernetes
  • Deploy production ML workloads on GCP using Vertex AI
  • Build and deploy a RAG-based LLM application as a production API
  • Monitor production AI systems with Prometheus and Grafana
  • Graduate with a portfolio of 10+ real-world projects

Prerequisites

Before you start, you should have:

  • Basic programming knowledge (any language)
  • Familiarity with the command line / terminal
  • No ML or cloud experience required

Ready to master AI Engineering Foundations?

Download the full syllabus or chat with us on WhatsApp.

WhatsApp Us