roadmaps that work
structured paths that actually get you somewhere. track your progress, no account needed.
LLM Foundations
get the fundamentals right. no shortcuts, just real understanding
duration: 2 weeks
Week 1: Core Concepts
Week 2: Architecture & Training
RAG to Production
from prototype to production. real systems, real problems, real solutions
duration: 2 weeks
Week 1: RAG Fundamentals
Week 2: Production Deployment
Conversational AI
build chatbots and voice assistants that actually work. memory, context, and real conversations
duration: 3 weeks
Week 1: Foundations
Week 2: Memory & Context
Week 3: Production Systems
Local LLM Deployment
run llms on your own hardware. privacy, cost control, and full ownership
duration: 3 weeks
Week 1: Model Selection & Quantization
- Choosing the Right Model
- Quantization Techniques (GGUF, AWQ)
- Hardware Requirements & Optimization
Week 2: Deployment Frameworks
- Ollama & LM Studio Setup
- vLLM for Production Serving
- Docker & Kubernetes Deployment
Week 3: Optimization & Monitoring
- Performance Tuning
- Cost Analysis & Resource Management
- Monitoring Local LLM Systems
MLOps for LLMs
deploy, monitor, and iterate on llm systems. the complete production lifecycle
duration: 4 weeks
Week 1: ML Lifecycle & Versioning
Week 2: CI/CD for ML
Week 3: Infrastructure & Orchestration
Week 4: Monitoring & Drift Detection
AIOps & Observability
monitor ai systems in production. metrics, alerts, and observability that actually help
duration: 3 weeks
Week 1: Observability Stack
Week 2: Monitoring & Alerting
Week 3: Anomaly Detection & Automation
Fine-tuning & Evaluation
adapt models to your domain. when to fine-tune, when not to, and how to do it right
duration: 3 weeks
Week 1: Fine-tuning Fundamentals
Week 2: Training & Optimization
Week 3: Evaluation & Deployment
AI Agents & Tool Use
build agents that use tools, plan, and reason. multi-agent systems and autonomous ai
duration: 4 weeks