With GenAI approaching at a rapid rate and everyone trying to find the most optimal ways to implement AI into their products and workflows, theres never been a better time to learn AI Engineering.
What is AI Engineering?
AI Engineering is the process of designing and implementing AI systems using pre-trained models and existing AI tools to solve practical problems. AI Engineers focus on applying AI in real-world scenarios, improving user experiences, and automating tasks, without developing new models from scratch. They work to ensure AI systems are efficient, scalable, and can be seamlessly integrated into business applications, distinguishing their role from AI Researchers and ML Engineers, who concentrate more on creating new models or advancing AI theory.
AI Engineer vs ML Engineer
An AI Engineer uses pre-trained models and existing AI tools to improve user experiences. They focus on applying AI in practical ways, without building models from scratch. This is different from AI Researchers and ML Engineers, who focus more on creating new models or developing AI theory.
AI Engineering Roadmap
The following is a list of popular topics related to AI Engineering, for a more in depth and interactive roadmap, visit the official AI Engineering roadmap.
Common Terms
- LLMs
- Inference
- Training
- Embeddings
- Vector Databases
- RAG
- Prompt Engineering
- AI Agents
- AI vs AGI
Using Pre-trained Models
- Pre-trained Models
- Benefits of Pre-trained Models
- Limitations and Considerations
- Popular AI Models
Open AI Models
- Capabilities / Context Length
- Cut-off Dates / Knowledge
Other Popular Models
- Anthropic's Claude
- Google's Gemini
- Azure AI
- AWS Sagemaker
- Hugging Face Models
- Mistral AI
- Cohere
OpenAI Platform
- OpenAI API
- Chat Completions API
- Writing Prompts
- OpenAI Playground
- Fine-tuning
- Managing Tokens
- Maximum Tokens
- Token Counting
- Pricing Considerations
AI Safety and Ethics
- Understanding AI Safety Issues
- Prompt Injection Attacks
- Bias and Fairness
- Security and Privacy Concerns
- Conducting Adversarial Testing
- OpenAI Moderation API
- Adding End-user IDs in Prompts
- Robust Prompt Engineering
- Know your Customers / Use Cases
- Constraining Outputs and Inputs
- Safety Best Practices
Open Source AI
- Open vs Closed Source Models
- Popular Open Source Models
- Hugging Face
- Hugging Face Hub
- Hugging Face Tasks
- Finding Open Source Models
- Using Open Source Models
- Inference SDK
- Transformers.js
- Ollama
- Ollama Models
- Ollama SDK
Embeddings
- Semantic Search
- Recommendation Systems
- Anomaly Detection
- Data Classification
Embeddings & Vector Databases
- Use Cases for Embeddings
- OpenAI Embeddings API
- OpenAI Embedding Models
- Pricing Considerations
- Open-Source Embeddings
- Sentence Transformers
- Models on Hugging Face
Vector Databases
- Purpose and Functionality
- Popular Vector DBs
- Chroma
- Pinecone
- Weaviate
- FAISS
- LanceDB
- Qdrant
- Supabase
- MongoDB Atlas
- Indexing Embeddings
- Performing Similarity Search
- Implementing Vector Search
RAG & Implementation
- RAG Use Cases
- RAG vs Fine-tuning
- Chunking
- Embedding
- Vector Database
- Retrieval Process
- Generation
- Implementing RAG
- Ways of Implementing RAG
- Using SDKs Directly
- LangChain
- Llama Index
- OpenAI Assistant API
- Replicate
Prompt Engineering
- ReAct Prompting
- Manual Implementation
- OpenAI Functions / Tools
- OpenAI Assistant API
- Building AI Agents
Multimodal AI
- Multimodal AI Use Cases
- Image Understanding
- Image Generation
- Video Understanding
- Audio Processing
- Text-to-Speech
- Speech-to-Text
- Multimodal AI Tasks
- OpenAI Vision API
- DALL-E API
- Whisper API
- Hugging Face Models
- LangChain for Multimodal Apps
- LlamaIndex for Multimodal Apps
- Implementing Multimodal AI
Next Steps
At roadmap.sh we have the comprehensive AI Engineering roadmap as well as the following that can help you on your travels!
Top comments (1)
Great