Generative AI
From transformers and LLMs to production RAG, prompt engineering, fine-tuning, deployment and orchestration with LangChain & LlamaIndex — the current, job-ready GenAI engineering stack.
Build with the current GenAI stack
A prerequisite-first path: Python, ML and neural network foundations, then a full climb through modern LLMs, prompting, fine-tuning, retrieval and orchestration.
This course starts with a Module 0 prerequisite track covering Python, AI/ML foundations, ANNs, CNNs, RNNs and attention/transformers — so you're not left guessing at the theory underneath modern LLMs. From there, it moves into the actual GenAI engineering stack: how LLMs work, how to access and compare them, how to prompt and fine-tune them, how to hook them up to your own data with RAG, and how to orchestrate all of it with LangChain and LlamaIndex.
- Prerequisite track included: Python refresher, AI/ML foundations, ANN/CNN/RNN and attention & transformers before the core GenAI modules.
- The full modern stack: LangChain, LlamaIndex, Hugging Face, vector databases (Chroma, FAISS, Pinecone, Qdrant), and LoRA/QLoRA fine-tuning.
- Capstone project: an end-to-end build spanning data ingestion, retrieval and a deployed, production-ready application.
Frequently Asked Questions
Do I need prior coding or AI/ML experience to join?
The course includes a Module 0 prerequisite track covering Python fundamentals, AI/ML foundations, and neural network basics (ANN, CNN, RNN, attention & transformers) before the core Generative AI modules begin, so you don't need prior GenAI experience — but basic programming comfort helps.
Is this a live course or self-paced?
It's delivered as live, mentored sessions in small cohorts — not pre-recorded videos.
Does this course cover deployment?
Yes. Module 8 covers LLM hosting and deployment on AWS SageMaker, API Gateway, Lambda and ECS Fargate, as well as local hosting with Ollama, Llama.cpp and LM Studio.
What frameworks and tools will I use?
LangChain and LlamaIndex for orchestration, Hugging Face for models and fine-tuning, and vector databases including Chroma, FAISS, Qdrant, Pinecone and LanceDB for retrieval.
Is there a capstone project?
Yes — an end-to-end capstone that brings together data ingestion, retrieval and a deployed, production-ready GenAI application.
Who teaches this course?
NavAiEra courses are taught by the NavAiEra team, led by founder Yogita Patil, an AI/ML educator and consultant.
Ready to build with GenAI?
Live, mentored cohorts starting soon — reserve your seat or ask us anything before you enrol.