Back to Programs
🏗️Leadership
AI Architect
System Design for AI at Scale
A program for senior engineers and tech leads who need to make architectural decisions for AI systems. You will evaluate LLM options, design scalable RAG architectures, plan knowledge graph strategies, model costs and ROI, and lead AI teams through build-vs-buy decisions at enterprise scale.
Duration
3 months
Level
Advanced
Starts
September 15, 2026
Modules
4 modules
What You'll Learn
AI system design patterns & trade-offs
LLM selection & evaluation frameworks
Scalable RAG architecture design
Knowledge Graph strategy & governance
Cost modeling & ROI analysis
Technical leadership for AI teams
Full Curriculum
Detailed Syllabus
01
Weeks 1–3
AI System Design Patterns
- End-to-end AI system architecture patterns
- LLM selection criteria: cost, latency, quality trade-offs
- Build vs. buy decisions for AI components
- Data architecture for AI: lakes, warehouses, feature stores
- Security and compliance in AI systems (SOC2, GDPR, HIPAA)
02
Weeks 4–6
RAG & Retrieval Architecture
- Designing scalable retrieval pipelines
- Vector database selection and capacity planning
- Multi-tenant RAG architectures
- Caching strategies and query optimization
- Evaluation framework design for retrieval quality
03
Weeks 7–9
Knowledge Systems & Agents at Scale
- Knowledge graph architecture for enterprises
- Agent orchestration patterns and failure modes
- Governance frameworks for autonomous AI systems
- Monitoring, alerting, and incident response
- Scaling agents: rate limiting, cost caps, circuit breakers
04
Weeks 10–12
Technical Leadership & Strategy
- AI roadmap planning and milestone definition
- Team structure and hiring for AI engineering
- Cost modeling: GPU compute, API costs, storage
- ROI frameworks for AI projects
- Capstone: Present an AI architecture proposal for a real use case
Outcomes
After this program, you'll be able to:
- Design enterprise-grade AI system architectures
- Make informed build-vs-buy decisions for AI components
- Lead AI engineering teams and set technical direction
- Build cost models and ROI frameworks for AI projects
- Implement governance and compliance for AI systems
Prerequisites
Before you start, you should have:
- 3+ years of software engineering experience
- Familiarity with cloud infrastructure (AWS/GCP/Azure)
- Basic understanding of ML/AI concepts