The Course
This is a four month, cohort based program designed for Software Engineers and DevOps Engineers who want to move into Generative AI without skipping fundamentals.
We start from the basics and do not assume prior knowledge of machine learning or artificial intelligence. The only prerequisite is a working knowledge of Python.
The course follows a learn by building approach. Each week includes hands on exercises that focus on real GenAI systems such as prompt and context engineering, retrieval augmented generation, fine tuning, model evaluation, and agents.
As the program progresses, you will go deeper into how language models work under the hood, including tokenization, attention, and training small language models from scratch.
By the end of the course, you will be able to design, build, and reason about Generative AI systems using an engineering mindset, not just tools or prompts.As you journey through the modules, you'll gain invaluable insights on applying your newfound prowess in real-world scenarios. From fine-tuning models to generate captivating narratives or designing stunning visuals, to predicting system failures before they occur, the practical applications are limitless. Not only will you walk away with a portfolio brimming with impressive, AI-driven projects, but you'll also be equipped with the strategic know-how to deploy AI solutions in a DevOps culture, enhancing efficiency and innovation. So, whether you aspire to revolutionize tech at a startup or spearhead change in an established enterprise, this course is your ticket to standing out in the rapidly evolving tech landscape.
What you will learn
This program gives you a clear and structured path from software and DevOps engineering into Generative AI, without skipping fundamentals.
You will start with the basics and gradually move toward building real GenAI systems. The focus is on understanding how things work, not just using tools.
By the end of the course, you will be able to:
• Design and implement prompt and context driven workflows
• Build retrieval based systems using vector databases
• Fine tune language models for narrow domains
• Evaluate model quality, cost, and latency tradeoffs
• Work with local and remote models using modern inference stacks
• Understand tokenization, attention, and training mechanics
• Build and train a small language model from scratch using PyTorch
• Reason about Generative AI systems like an engineer, not a user
All learning is hands on and backed by practical exercises using real tools and real infrastructure.
Curriculum
Your instructor
This course is taught by Prashant with over 20 years of experience across Software Engineering, DevOps, Cloud, Kubernetes, and large scale distributed systems.
Prashant has worked on production systems used by millions of users and has spent years designing, operating, and debugging complex infrastructure in real world environments. His recent work focuses on Generative AI systems, including how large language models work under the hood and how to build reliable GenAI systems from an engineering perspective.
He is the author of multiple technical books and holds several industry recognitions including CNCF Kubestronaut, Red Hat Certified Architect, and Amazon Web Services Community Builder.
This course reflects his belief that engineers should learn Generative AI by understanding fundamentals, building systems hands on, and working with real tools and real infrastructure rather than relying on abstract theory or prompt only workflows.
Transformative
Embrace the Future of AI: Evolve from Traditional Software to AI-Driven Engineering
Pioneering
Charting New Territories: From DevOps Mastery to Leading-Edge AI Engineering