|$ curl https://forge-ai.dev/api/markdown?path=docs/roadmaps/ai
$cat docs/ai-engineering-learning-roadmap.md
updated Today·10 min read·published

AI Engineering Learning Roadmap

AIRoadmapAll Levels
Introduction

Complete AI Engineering learning path from LLM fundamentals and prompt engineering through RAG, agents, fine-tuning, and production deployment.

info

AI engineering builds on web fundamentals. Complete the HTML, CSS, and JS roadmaps first, then dive into AI.
Full AI Engineering Roadmap
6
Training & Production~12 hoursProfessional

Fine-tune custom models, evaluate rigorously, and operate safely in production.

$
Fine-tuning

Supervised fine-tuning of base models on custom datasets — LoRA, QLoRA, and full-parameter tuning with modern frameworks

$
SFT / DPO / RLHF

Comparing training paradigms — supervised fine-tuning, direct preference optimization, and reinforcement learning from human feedback

$
Dataset Curation

Sourcing, cleaning, deduplicating, and augmenting high-quality datasets for instruction tuning and preference alignment

$
Evaluation & Benchmarks

Systematic evaluation strategies — benchmark suites, human evaluation, LLM-as-judge, and task-specific metrics for quality assurance

$
Distillation

Knowledge distillation techniques — training smaller student models from larger teacher models to reduce cost and latency

$
Guardrails & Safety

Implementing content filters, input/output validation, topic restrictions, and adversarial prompt detection for safe deployment

$
Monitoring & Observability

Tracing LLM calls, logging prompts and responses, tracking token usage, alerting on drift, and debugging production issues

$
Caching & Latency

Semantic caching of LLM responses, prefix caching, speculative decoding, and batching to minimize time-to-first-token

$
Rate Limiting

Managing API rate limits with queuing, retry backoff, token-bucket algorithms, and multi-key rotation strategies

$
Multimodal

Working with models that process images, audio, and video alongside text — vision encoders, CLIP, and multimodal generation

$
Reasoning & Planning

Advanced reasoning techniques — tree-of-thought, ReAct, tool-augmented reasoning, and self-consistency for complex problem solving

$
Code Generation

Leveraging LLMs for code synthesis, repair, and refactoring — repository-level context, execution feedback, and test generation

$
AI Security

Securing AI systems against prompt injection, data exfiltration, model theft, and supply chain attacks on LLM pipelines

$
Ethics & Alignment

Responsible AI principles — bias mitigation, transparency, fairness auditing, and alignment with human values and regulations

$Blueprint — Engineering Documentation·Section ID: RES-05·Revision: 1.0