Builds products on top of large language models — retrieval pipelines, assistants and AI features inside existing software. Less model training than model application: the hard part is making a probabilistic system behave reliably in production.
Also advertised as: Generative AI Engineer, LLM Engineer, Applied AI Engineer.
What the job involves
Design and ship retrieval-augmented generation (RAG) pipelines over company data
Choose models and tune inference controls for cost, latency and reliability
Defend against prompt injection and unsafe output before anything reaches users
Evaluate AI features with real test sets rather than impressions
Integrate model APIs into existing products and own them in production
Skills this role needs
These are the actual modules taught on the tracks that train for this role — not a generic skills list.
AI Foundations — optional basics (free)
Module 0 — Foundations: How AI Works & the GenAI Toolkit
Foundations of Generative AI
Large Language Models Deep Dive
Prompt Engineering Mastery
Building with LLM APIs
Retrieval-Augmented Generation (RAG)
AI Agents & Tool Use
Fine-tuning & Embeddings
Production AI Systems
Context Engineering
Modern LLM Architectures
Voice & Multimodal Agents
Module 0 — Foundations: Logic, Probability & Algorithms for AI
