
- Home
- Books
- AI Engineering
- AI Deployment & Performance
- LLM Engineer's Handbook
AI Deployment & PerformanceIn Stock
LLM Engineer's Handbook
Master the art of engineering large language models from concept to production
Price৳ 300
LLM Engineer's Handbook by Paul Iusztin is a practical guide to building, fine-tuning, and deploying production large language model applications. The book covers the full lifecycle of generative AI systems through the concrete construction of an end-to-end LLM application. Readers work through streaming data ingestion, synthetic dataset generation, fine-tuning techniques, and production inference optimization.
What you will learn
- Construct automated data pipelines to extract, clean, and embed multi-modal documents
- Fine-tune open-weight models using supervised training, LoRA, and QLoRA adapters
- Align models with direct preference optimization and reinforcement learning techniques
- Build hybrid retrieval-augmented generation pipelines using vector stores and rerankers
- Optimize production model inference with vLLM, TensorRT-LLM, and quantization
- Implement continuous monitoring, evaluation harnesses, and LLMOps deployment workflows
Who this is for
Machine learning engineers, backend developers, and data scientists building production generative AI systems. Working knowledge of Python and basic machine learning concepts is expected. Prior large language model fine-tuning experience is not required.


