Skip to content
AI Masters DoJo
ExploreMenu
Book a discovery call

AI engineering

AI Engineering: Model Tuning, Deep Learning and Agents

Explore model tuning, neural networks, transformers, fine-tuning and AI agent development.

A small sample of 30,000+ courses curated from around the world, all available to DoJo members.

Book a discovery callExplore DoJo membership

A free 30-minute conversation with Ted about your goals.

Already a member? Open this course

Course topics

AI engineering

  • Model tuning
  • Deep learning
  • MLOps

You evaluate the results

Find your fit

Is this a useful starting point?

For experienced Python learners with machine-learning, deep-learning and mathematical foundations.

Starting point
Expert
Course length
15.5 total hours
Lessons
61 lectures

Course by School of AI

Course last updated: 02/2026

Requirements
  • Completion of a beginner or associate-level AI or machine learning course (or equivalent knowledge)
  • Strong understanding of Python programming, including experience with functions, classes, and working with libraries like NumPy and Pandas
  • Solid grasp of basic machine learning concepts, including regression, classification, model evaluation, and overfitting
  • Familiarity with deep learning fundamentals, including neural networks and basic model architecture
  • Prior exposure to tools like Jupyter Notebook, TensorFlow, or PyTorch
  • Working knowledge of mathematics for AI, including linear algebra, probability, and calculus
  • A computer (Windows, macOS, or Linux) with reliable internet and the ability to install development tools
  • Willingness to explore complex, production-grade systems and invest time in hands-on coding, model experimentation, and deployment workflows
What is included
  • Role Play
  • 15.5 hours on-demand video
  • 46 downloadable resources
  • Access on mobile
  • Certificate of completion

DoJo membership: A$250 per month per seat, excluding GST. Includes fortnightly group support and a private member community.

Explore the lessons

Course curriculum.

9 sections • 61 lectures • 15h 24m total length

Introduction to Course and Instructor2 lectures • 7min
  1. Certificate of Completion00:29
  2. What You’ll Learn in the AI Engineer Professional Certificate Course06:24
Model Tuning and Optimization7 lectures • 2hr 5min
  1. Day 1: Introduction to Hyperparameter Tuning13:46
  2. Day 2: Grid Search and Random Search16:09
  3. Day 3: Advanced Hyperparameter Tuning with Bayesian Optimization26:57
  4. Day 4: Regularization Techniques for Model Optimization13:17
  5. Day 5: Cross-Validation and Model Evaluation Techniques13:00
  6. Day 6: Automated Hyperparameter Tuning with GridSearchCV and RandomizedSearchCV19:28
  7. Day 7: Optimization Project – Building and Tuning a Final Model22:45
  8. Tuning and Validating the Final Model for Loan Approval Prediction
Convolutional Neural Networks (CNNs)7 lectures • 2hr 40min
  1. Day 1: Introduction to Convolutional Neural Networks26:16
  2. Day 2: Convolutional Layers and Filters23:48
  3. Day 3: Pooling Layers and Dimensionality Reduction23:58
  4. Day 4: Building CNN Architectures with Keras and TensorFlow17:46
  5. Day 5: Building CNN Architectures with PyTorch22:26
  6. Day 6: Regularization and Data Augmentation for CNNs18:39
  7. Day 7: CNN Project – Image Classification on Fashion MNIST or CIFAR-1027:34
  8. Presenting a CNN Image Classifier for Fashion Product Categorization
Recurrent Neural Networks (RNNs) and Sequence Modeling7 lectures • 2hr 45min
  1. Day 1: Introduction to Sequence Modeling and RNNs33:32
  2. Day 2: Understanding RNN Architecture and Backpropagation Through Time (BPTT)24:31
  3. Day 3: Long Short-Term Memory (LSTM) Networks15:03
  4. Day 4: Gated Recurrent Units (GRUs)07:07
  5. Day 5: Text Preprocessing and Word Embeddings for RNNs24:02
  6. Day 6: Sequence-to-Sequence Models and Applications43:09
  7. Day 7: RNN Project – Text Generation or Sentiment Analysis17:55
  8. Designing an RNN for Sentiment Analysis of Customer Reviews
Transformers and Attention Mechanisms7 lectures • 2hr 14min
  1. Day 1: Introduction to Attention Mechanisms15:17
  2. Day 2: Introduction to Transformers Architecture18:19
  3. Day 3: Self-Attention and Multi-Head Attention in Transformers21:00
  4. Day 4: Positional Encoding and Feed-Forward Networks20:21
  5. Day 5: Hands-On with Pre-Trained Transformers – BERT and GPT19:37
  6. Day 6: Advanced Transformers – BERT Variants and GPT-320:38
  7. Day 7: Transformer Project – Text Summarization or Translation18:33
  8. Deploying a Transformer Model for Text Summarization in LegalTech
Transfer Learning and Fine-Tuning7 lectures • 2hr 19min
  1. Day 1: Introduction to Transfer Learning14:52
  2. Day 2: Transfer Learning in Computer Vision26:26
  3. Day 3: Fine-Tuning Techniques in Computer Vision21:46
  4. Day 4: Transfer Learning in NLP17:00
  5. Day 5: Fine-Tuning Techniques in NLP26:04
  6. Day 6: Domain Adaptation and Transfer Learning Challenges14:52
  7. Day 7: Transfer Learning Project – Fine-Tuning for a Custom Task18:22
  8. Fine-Tuning a Pretrained Model for Industry-Specific Email Classification
AI Agents: A Comprehensive Overview6 lectures • 1hr 24min
  1. 1. Hands-on AutoGen | IBM Bee | LangGraph | CrewAI | AutoGPT08:46
  2. 2. Hands-on AutoGen13:04
  3. 3. Hands-on IBM Bee Framework18:23
  4. 4. Hands-on LangGraph20:05
  5. 5. Hands-on CrewAI15:36
  6. 6. Hands-on AutoGPT07:52
  7. Selecting the Right Multi-Agent Framework for an AI Research Assistant
Introduction and Hands-on MLOps17 lectures • 1hr 48min
  1. 1. Introduction to MLOps Sessions00:37
  2. 2. Overview of MLOps and its Importance01:29
  3. 3. Evolution of Machine Learning Operations01:06
  4. 4. Key Concepts in MLOps: Versioning, Automation, and Monitoring01:22
  5. 5. MLOps vs. DevOps: Similarities and Differences01:12
  6. 6. Hands-on: Set up a basic MLOps Project Structure (Git, Docker, Model Pipeline20:37
  7. 7. Introduction to Data Science to Production Pipeline Section00:24
  8. 8. Overview of the ML Workflow: Data Preparation to Deployment03:11
  9. 9. Experimentation vs. Production01:51
  10. 10. Challenges in Deploying ML Models00:58
  11. 11. Hands-on: Build an end-to-end pipeline for an ML model21:06
  12. 12. Introduction to Infrastructure for MLOps Section00:36
  13. 13. Introduction to Cloud Platforms (AWS, GCP, Azure)04:13
  14. 14. Containerization with Docker01:21
  15. 15. Kubernetes for Orchestrating ML Workloads01:20
  16. 16. Setting up Local MLOps Environments01:25
  17. 17. Hands-on: Containerize simple ML model & deploy it locally using Kubernetes45:41
  18. Reviewing Your First End-to-End MLOps Pipeline for Deployment
Final Quiz & Congratulations1 lecture • 1min
  1. Final Quiz 100 questions
  2. Congratulations and Best of Luck00:47

From learning to practice

Try this next.

Follow a model-tuning exercise and compare its results with the original configuration.

A useful next step

Choose where to start.

Talk through your goals in a free 30-minute discovery call with Ted. Bring a task you want to improve and the tools you already use.

Book a discovery callExplore DoJo membership

More to explore

Find a course for your next task.

Browse the course sample