Please note that this list of topics is based on our standard course offering, evolved from current industry uses and trends. We will work with you to tune this course and level of coverage to target the skills you need most. Course agenda, topics and labs are subject to adjust during live delivery in response to student skill level, interests and participation. The course tools, topics, use cases and hands-on labs can also be easily adjusted to suit your specific needs, goals or requirements. Please inquire for details and options.
Introduction to MLOps
Learn why MLOps matters and how it connects data science and operations to bring machine learning models smoothly into real-world use.
- MLOps: The key to integrating data science with operations for AI model efficiency
- Understanding the need for MLOps
- Differences between MLOps, DevOps, and DataOps
- MLOps lifecycle overview
MLOps Tools and Techniques
Get familiar with the key tools and practices that help you build, manage, and improve machine learning pipelines with confidence.
- Review essential tools and practices for building effective and sustainable ML pipelines
- Overview of MLOps tools (MLflow, Kubeflow, etc.)
- MLOps pipeline components
- MLOps best practices
- Walking through a simple machine learning pipeline
Automating Machine Learning Workflows
Discover how to save time and improve results by automating important steps in your machine learning workflows.
- Explore the importance of automating ML workflows for improved efficiency and model deployment
- The role of automation in MLOps
- Continuous Integration and Continuous Deployment (CI/CD) in machine learning
Model Monitoring and Management
Find out how to keep an eye on your models, catch performance issues early, and keep them running at their best.
- Understanding model decay and why it matters
- Continuous performance monitoring and anomaly detection
- Data drift and concept drift analysis
- Implementing feedback loops for continuous improvement
- Learn how to track, organize, and safely update your models so you always know what’s running in production.
MLflow in Practice
See how to use MLflow to log, compare, and fine-tune your experiments, making it easier to learn what works and what doesn’t.
- Setting up MLflow tracking servers and UI
- Organizing experiments, runs, and hyperparameter tuning
- Capturing parameters, metrics, and artifacts
- Visualizing and comparing experiment results
Orchestration and Pipelines
Explore how to design smart, automated pipelines that help your machine learning projects run smoothly and reliably.
- Understanding the role of orchestration in MLOps
- Setting up workflows and pipelines using tools like Prefect
- Adding retries, notifications, and caching
- Enabling collaboration across teams and workflows
Foundations of AI and Secure Coding
Understand the basics of AI and why secure coding is critical when building or working with AI-powered applications.
- Exploring the intersection of AI and software security
- Key concepts: machine learning, deep learning, LLMs, generative AI
- Real-world examples of AI in web applications
- Why AI awareness matters for secure coding and design
Secure Coding Principles in the Age of AI
Learn how to write and check code that keeps AI systems safe from common and emerging risks.
- Identifying AI-specific coding vulnerabilities
- Applying OWASP principles to AI systems
- Securing data pipelines, model inputs, and outputs
- Implementing output constraints and validation
How AI Attacks Your Code, Systems, and Teams
See how attackers use AI to find weak spots—and how you can recognize and reduce these risks.
- Understanding AI-powered attack techniques
- Prompt injection, data poisoning, and model evasion
- Risks from AI-generated code and API abuse
- Human-in-the-loop risks and social engineering amplification
Defending Against AI-Powered Attacks
Build practical strategies for protecting your systems and data from AI-driven threats.
- Building AI-aware threat models
- Mapping risks to practical defenses and controls
- Monitoring and logging for AI systems
- Tools and strategies for securing the software supply chain
Secure AI Integration in Web Applications
Learn how to safely connect AI models to your web applications without adding new security holes.
- Managing risks of integrating AI in web apps
- Securing API interactions and data protection
- Validating and sanitizing inputs and outputs
- Avoiding common integration pitfalls
Natural Language Processing (NLP) and AI Security Risks
Understand the unique risks that come with NLP tools and how to use them safely in your work.
- Understanding NLP and its widespread use
- Mitigating prompt injection, data leakage, and context hijacking
- Using NLP tools responsibly in security workflows
- Implementing safeguards for NLP models in production
AI Risk Management and Security Leadership
Discover how to guide teams and organizations toward smart, responsible, and secure AI use.
- Applying governance frameworks to manage AI risk
- Incorporating AI into the secure development lifecycle (SDLC)
- Establishing guardrails and policy approaches
- Evaluating AI tools and leading responsible adoption
Bonus: Staying Safe with AI Tools at Work
Pick up practical tips to help yourself and your team use popular AI tools safely and responsibly on the job.
- Recognizing risks of workplace AI tools (e.g., ChatGPT, Copilot)
- Best practices for safe AI use on the job
- Protecting data, intellectual property, and organizational reputation
- Tips for guiding teams on responsible AI adoption
Addendum: Resources, Insights & Tip Guides
