Dont just learn AI.....
Build, Productionalize and Improve it!
Master Generative AI with AppliedGenAi
Course categories
Pick a subject and start learning
What is Advanced Gen AI Workflows?
The Advanced Gen AI Workflows course is designed for professionals who want to go beyond theory and truly master building, deploying, and scaling modern AI applications. We dive deep into Large Language Models (LLMs), LangChain, LangGraph, Retrieval-Augmented Generation (RAG), and Multi-Agent Systems, while also covering critical production aspects that most courses overlook.
You’ll not only learn to design intelligent systems like chatbots, recommendation engines, and multi-agent frameworks, but also gain hands-on expertise in real-world deployment. We’ll cover:
-
API Protocols in Action: REST, WebSocket, and gRPC—applied to RAG and agent systems.
-
Cloud-Native Deployments: Running open-source LLMs on GPUs in AWS EKS with Terraform and load testing.
-
Scalable RAG Applications: Deploying on AWS Fargate and Lambda with CI/CD pipelines using Terraform along with monitoring and alerting framework
-
Monitoring & Metrics: Ensuring reliability, observability, and continuous improvement in production.
By the end of this course, you’ll have the skills to take AI projects from prototype to production at scale, making you stand out as someone who doesn’t just build AI—but engineers it for real-world impact.
Generate SQL from Natural Language
Build a LangGraph based multi-agent system that turns text into SQL. Start with 8 SQL tables and learn to scale, deploy, monitor, and refine it for real-world use.
Health Insurance Policy Recommendation
Build a LangGraph multi-agent system that recommends health insurance plans from over 100 options, based on user preferences.
Deployment and Monitoring
Agentic systems
Deploy RAG to AWS Fargate using Terraform with monitoring via CloudWatch. Set up CI/CD pipeline for automated updates, safe rollbacks. Deploy open source LLM's on Kubernetes and monitor alerts.
What is LLM Internals and Optimization?
 The LLM Internals and Optimization course is designed to provide a deep dive understanding into the architecture, training, fine-tuning and human alignment strategies that are a part of conversational AI applications.
While learning different methods that improve LLM’s, we will also implement all these methods on health insurance policy documents and compare different strategies. The main aim of this course is to build a solid mathematical foundation of internals of conversational ai applications. We will be implementing all these methods on GPU enabled clusters.
Fine-Tune Language Models
We will understand and implement different finetuning strategies like LORA, QLORA, REFT and DORA. We will take different health insurance policy documents and implement these strategies and understand different nuances in using them.
Reinforcement Learning Optimization
We’ll focus deeply on Reinforcement Learning—starting from core concepts like Bellman equations, Monte Carlo, and TD learning advancing to human alignment methods like RLHF, DPO, IPO, KTO, and ORPO. All techniques will be applied to health insurance policy documents.
Unlock the Power of Generative AI with AppliedGenAi
Reviews (WIP)
Take Your AI Skills to the Next Level
Master Generative AI with industry-focused courses designed for real-world applications. Gain hands-on experience, learn from expert instructors, and stay ahead in the AI revolution.
