Build production-ready generative AI applications using advanced language models.
LLM Fine-Tuning
Adapt foundation models to your domain and data.
Lessons
- SFT, LoRA, and QLoRA in practice
- Dataset curation & filtering
- Preference tuning (DPO/RLHF basics)
- Eval harnesses & regression testing
You will be able to
- Fine-tune a model on a domain dataset
- Score it on a reproducible eval suite
Prompt Engineering
Systematically design and test prompts at scale.
Lessons
- Prompt patterns & anti-patterns
- Structured outputs & function calling
- Prompt evals and A/B testing
- Cost, latency, and caching
You will be able to
- Deliver a versioned prompt library
- Measure quality vs. cost trade-offs
RAG Systems
Ground LLMs in your own knowledge with retrieval.
Lessons
- Chunking, embeddings, and vector stores
- Hybrid retrieval & reranking
- Grounded generation & citations
- Guardrails and hallucination checks
You will be able to
- Ship a production RAG pipeline
- Instrument groundedness & recall metrics
Multi-Modal AI
Combine text, vision, audio, and structured data.
Lessons
- Vision-language models overview
- Speech in and out
- Tool use & agents with modalities
- Evaluating multi-modal outputs
You will be able to
- Prototype a multi-modal assistant
- Evaluate quality across modalities