Skip to content

javabuddy/best-ai-and-llm-engineering-resource

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
LICENSE
LICENSE
 
 
README.md
README.md
 
 

Repository files navigation

Best AI and LLM Engineering Resources

Welcome to Best AI and LLM Engineering Resources — a curated collection of high-quality books, courses, and learning materials to help software engineers, data scientists, and AI enthusiasts master Large Language Models (LLMs), Prompt Engineering, AI System Design, and Machine Learning Engineering.

This repository aims to provide reliable resources that can guide you in building, deploying, and optimising LLMs and AI systems for production.

📚AI and LLM Engineering Books

Books are gret way to start your AI journey, especially if you want to transition form Software Engineer to AI Engineer. Here are 10 must-read AI and LLM engineering books for developers:

  1. The LLM Engineering Handbook by Paul Iusztin and Maxime Labonne
  2. AI Engineering by Chip Huyen
  3. Designing Machine Learning Systems by Chip Huyen
  4. Building LLMs for Production by Louis-François Bouchard and Louie Peters
  5. Build a Large Language Model (from Scratch) by Sebastian Raschka, PhD
  6. Hands-On Large Language Models: Language Understanding and Generation
  7. Prompt Engineering for LLMs
  8. Building Agentic AI Systems
  9. Prompt Engineering for Generative AI
  10. The AI Engineering Bible

📘 AI and LLM Engineering Courses

Udemy

  1. LLM Engineering: Master AI, Large Language Models & Agents
  2. LangChain- Develop LLM-powered applications with LangChain
  3. Complete Generative AI Course With Langchain and Huggingface
  4. Artificial Intelligence A-Z™: Learn How To Build An AI
  5. The Complete Artificial Intelligence and ChatGPT Course
  6. Machine Learning A-Z™: Hands-On Python & R In Data Science
  7. Deep Learning A-Z™: Hands-On Artificial Neural Networks
  8. Generative AI for Beginners
  9. Open-source LLMs: Uncensored & secure AI locally with RAG
  10. AI-Agents: Automation & Business with LangChain & LLM Apps

Educative

  1. Become an LLM Engineer (Skill Path | Best for Engineers & Developers)
  2. Grokking AI for Engineering & Product Managers (Best for Tech Leads and PMs)
  3. Generative AI Essentials (Best for Beginners & Tech Enthusiasts)
  4. Generative AI Essentials (Best for Beginners & Tech Enthusiasts)
  5. Code Smarter with Cursor AI Editor (Best for VS Code Users & Productivity-Focused Developers)
  6. Become an Agentic AI Expert (New Skill Path)

Couresra

Here are some of the best courses to master AI, LLMs, and their applications:

YouTube Videos to Learn LLM and Agentic AI

  1. LLM Introduction: https://www.youtube.com/watch?v=zjkBMFhNj_g

  2. LLMs from Scratch: https://www.youtube.com/watch?v=9vM4p9NN0Ts

  3. Agentic AI Overview (Stanford): https://www.youtube.com/watch?v=kJLiOGle3Lw

  4. Building and Evaluating Agents: https://www.youtube.com/watch?v=d5EltXhbcfA

  5. Building Effective Agents: https://www.youtube.com/watch?v=D7_ipDqhtwk

  6. Building Agents with MCP: https://www.youtube.com/watch?v=kQmXtrmQ5Zg

  7. Building an Agent from Scratch: https://www.youtube.com/watch?v=xzXdLRUyjUg

  8. Philo Agents: https://www.youtube.com/playlist?list=PLacQJwuclt_sV-tfZmpT1Ov6jldHl30NR

🌐 Best Places to Learn AI and LLM

If you are looking for platforms that offer comprehensive AI and LLM learning materials, explore these:

  • Coursera
    University-level AI/ML/LLM courses, specialisations, and professional certificates.

  • DeepLearning.AI
    Specialises in AI/LLM courses by leading practitioners, including Andrew Ng.

  • Hugging Face
    The best place to learn practical NLP, transformers, and LLMs from the creators of leading open-source libraries.

  • Udacity
    Offers AI nanodegree programs focusing on deep learning, NLP, and production AI systems.

  • Fast.ai
    A free, practical deep learning course that teaches how to build and deploy models efficiently.

  • Hugging Face Transformers Documentation
    Go-to resource for learning how to use LLMs and transformers in code.

AI and LLM Engineering Articles

🚀 Best AI and LLM Projects (Ideas to Build & Learn)

Building projects is the best way to cement your learning. Here are some small to medium-sized project ideas to try:

Beginner Projects

  • Sentiment Analysis Tool
    Build a tool to detect sentiment (positive/negative/neutral) from tweets or product reviews using transformers or classical NLP.

  • AI-Powered Text Summariser
    Use models like T5 or BART to summarise long articles into a few sentences.

  • Chatbot with GPT-4 API
    Create a basic conversational bot using OpenAI’s API for fun or customer support use cases.

Intermediate Projects

  • Question Answering System
    Build a system that can answer user queries based on a knowledge base or documents using LLMs.

  • AI Resume Screener
    Develop a tool that analyses resumes and provides summaries/highlights based on job descriptions.

  • Voice-to-Text Transcription using Whisper
    Use OpenAI’s Whisper model to convert speech from audio files into text.

Advanced Projects

  • Multi-modal AI App (Text + Image)
    Combine text and image inputs (like BLIP-2) to create a smart captioning or Q&A system.

  • Custom Fine-tuned LLM
    Fine-tune a pre-trained language model on domain-specific data (e.g., legal, medical) and deploy via API.

  • End-to-End AI Search Engine
    Build a mini search engine using embedding techniques (e.g., vector DBs + OpenAI embeddings) for semantic search.

Prompt Engineering Courses

Here are some of the best Udemy courses to start with:

TensorFlow Learning Resources

Here are some of the best TensorFlow courses and certifications to join:

💡 Best AI and LLM Engineering Interview Questions

Prepare for interviews with these commonly asked AI and LLM engineering questions:

  • Explain the architecture of a transformer model.
  • What are positional encodings and why are they important in transformers?
  • How would you fine-tune a large language model on a domain-specific dataset?
  • Discuss techniques for reducing hallucination in LLM outputs.
  • What are tokenizers? How do you choose one for your application?
  • Compare zero-shot, few-shot, and fine-tuning approaches for LLMs.
  • How do you evaluate the performance of an LLM-based system?
  • What are the trade-offs between pre-training and prompt engineering?
  • Describe challenges in deploying LLMs at scale.
  • How would you handle latency issues in a production LLM API?

🏗️ System Design for AI Engineering

When designing AI systems, these are key system design patterns and components to consider:

  • Model Serving Infrastructure: Design for high availability, low latency (e.g., TensorFlow Serving, TorchServe, custom API).
  • Vector Databases for Embeddings: Use tools like Pinecone, Weaviate, or Milvus for semantic search.
  • Inference Optimisation: Quantisation, pruning, distillation for faster inference.
  • Feature Store: A central repository for storing and sharing ML features (e.g., Feast, Tecton).
  • Batch vs Real-time Inference: Trade-offs between latency and throughput.
  • Monitoring and Feedback Loop: Continuous model monitoring, drift detection, and feedback for improvement.

📦 LLM Deployment Patterns

Common patterns for deploying large language models effectively:

  • API-as-a-Service: Wrap your LLM as a REST/gRPC API and deploy using cloud services or Kubernetes.
  • Edge Deployment: Run small or quantised models on edge devices (e.g., smartphones, IoT devices).
  • Hybrid Cloud + Edge: Serve large models from the cloud and lightweight components on-device.
  • Multi-Tenant Serving: Serve multiple models or versions using a shared infrastructure (e.g., using Seldon or KServe).
  • Sharded Serving: Split large models across multiple nodes for parallel inference.
  • Serverless LLM Inference: Use serverless platforms (e.g., AWS Lambda + Hugging Face) for cost-efficient scaling.

🚀 Productionisation of AI Systems

Things to consider when moving AI systems from prototype to production:

  • Model Versioning and CI/CD: Use tools like MLflow, DVC, or Weights & Biases for model tracking and deployment automation.
  • Latency and Throughput: Design APIs and infra for SLA adherence.
  • Scalability: Use autoscaling and load balancing (e.g., K8s, AWS SageMaker) for inference endpoints.
  • Monitoring: Set up metrics for input data drift, model performance degradation, and alerting.
  • Data Privacy and Security: Implement encryption at rest and in transit, role-based access control.
  • A/B Testing and Shadow Deployment: Safely roll out new models and gather feedback.

🛠️ Open-Source Libraries, Frameworks, and Toolkits

Here are some essential open-source tools for AI and LLM engineering:

AI and LLM Engineering RoadMap

e8daef35-b630-4f56-90d0-7b27ed261823_1200x1200

Feel free to contribute by submitting pull requests with high-quality resources!

License

This repository is licensed under the MIT License — see the LICENSE file for details. This means you are free to use, share, and build upon this work, provided you give appropriate credit.

Contribution Guidelines

If you know of a resource that fits this repository, kindly open a pull request. Please ensure that the resource is of high quality and preferably free or affordable for learners globally.

About

Best AI & LLM Engineering Resources

Resources

Readme

License

MIT license
Activity

Stars

182 stars

Watchers

2 watching

Forks

28 forks
Report repository

Releases

No releases published

Packages

 
 
 

Contributors