# Essential Skills for Becoming an AI Engineer: RAG, AI Agents, & More

## Executive summary

The video outlines the modern skill stack required for an AI Engineer, defining the role as building and deploying systems around existing Large Language Models (LLMs), rather than researching foundational models. The necessary skills are structured into three critical tiers: foundational engineering skills (Python, Git, APIs), specialized AI techniques (RAG, embeddings, agents), and deployment/operations expertise (Containerization, Observability). The speaker emphasizes that mastering this structured approach is crucial for building reliable, production-grade AI solutions.

## Key takeaways

- AI Engineer vs. ML Researcher: An AI Engineer builds applications using existing models (e.g., Frontier, Open Source), connecting them to data and tools. An ML Researcher focuses on training foundational models from scratch and publishing new architectures.
- The Three-Tier Skill Stack: The required skills are structured in three tiers: 1) Foundational skills (Python, Git, APIs); 2) AI-specific skills (Embeddings, RAG, Agents); and 3) Deployment/Ops skills (Containerization, Observability).
- The Importance of Grounding Data (RAG): Retrieval Augmented Generation (RAG) is critical for providing LLMs with accurate, company-specific information (e.g., policies, legal documents) to prevent hallucination. This involves chunking documents, embedding them into vectors, and feeding relevant context into the LLM's context window.
- AI Agents and Tool Use: AI Agents represent a significant advancement, allowing systems to dynamically decide next steps, call external tools, observe results, and iterate in a loop, moving beyond simple predefined workflows.

## Technical details

- Foundational Skills: Fluency in Python (for understanding packages like PyTorch and TensorFlow), Git for version control, command line utilities (CLIs), Linux operating system knowledge, and understanding Application Programming Interfaces (APIs) for programmatic model calls.
- Embeddings and Vector Search: Embeddings convert text (from formats like PDFs) into numerical vectors, allowing systems to search for meaning and similarity rather than just matching keywords. This is foundational for RAG.
- Deployment and Operations (Tier 3): Skills required for production include containerization (packaging agents/models), Kubernetes for deployment across hybrid clouds, Observability (understanding why an agent made a decision), and Monitoring (managing token usage and security).

## Practical implications

- Focus personal projects on the three most common production use cases: RAG knowledge systems, agents that query databases/visualize data, and deploying applications using modern AI tools.
- Build experience in the full lifecycle, from API design and vector storage to containerization and observability, to demonstrate comprehensive AI engineering capability.

## Topics

AI Engineering, RAG (Retrieval Augmented Generation), AI Agents, LLMs, System Architecture, DevOps/MLOps, AI Agents Guide, IBM AI Newsletter

Source: https://www.youtube.com/watch?v=XN3xNJvWXsc