AI-First Well-Architected Systems: Designing Cloud & AI Architectures- Full Day
In this full-day hands-on workshop, you’ll learn how to design and build systems that are AI-ready, cloud-native, and built to scale. Leveraging the latest from AWS’s Generative AI Lens, Salesforce’s Well-Architected for Data Cloud & Einstein, and other frameworks (Azure, Google Cloud, Databricks), you’ll gain the patterns, tools, and trade-offs to create resilient, efficient, and secure AI + cloud architectures.
Whether you're deploying inference APIs, building agentic systems, or transforming legacy workloads—walk away with design strategies and architecture playbooks you can apply immediately.
Audience Fit:
Cloud Architects → Apply WA pillars to AI workloads
AI/ML Engineers → Build inference & training pipelines with resiliency
DevOps/SRE → Implement observability, failover, scaling, and FinOps
Engineering Leaders → Drive org-wide adoption of AI-ready patterns
Workshop Method:
Level 1: Core WA pillars applied to AI
Level 2: Case studies + trade-off exercises (e.g., GPU cost vs latency, caching vs model freshness)
Hands-on: Group WA review of a sample AI system
Framework Coverage:
AWS: WA Generative AI Lens, Bedrock AgentCore, Prescriptive Guidance on agentic AI
Salesforce: Trusted / Easy / Adaptable + Einstein AI integrations
Google Cloud & Azure: AI/ML perspectives within WA frameworks
Databricks: Well-Architected Lakehouse guidance
Module 1 Foundations & Industry Frameworks - • What makes AI-native workloads different vs traditional cloud-native • Survey of Well-Architected frameworks (AWS, Salesforce, Azure, Google) and their AI/ML perspectives / lenses • Responsible AI, governance, data privacy baseline
Module 2: Reliability, Resilience & Observability • HA patterns for inference APIs and agents • Blast radius control & failure isolation • Recovery strategies (RTO, RPO, model fallback)
Module 3: Performance Efficiency & Scalability • Scaling strategies (vertical, horizontal, serverless triggers) • Bursty inference workloads • DBs, caches, embeddings – Trade-offs: GPU pooling vs autoscaling vs inference acceleration – Caching embeddings for RAG vs recomputation – CDN strategies for generative content – Benchmarking latency vs throughput in real-time agents
Module 4: Cost Optimization & Sustainability • Training vs inference cost trade-offs • Optimizing compute/storage • Spot instances & FinOps – Cost patterns: reserved vs spot vs serverless GPU bursts – Tracking AI spend across vector DBs, model hosting, orchestration layers – Rightsizing GPU/CPU balance – GreenOps: carbon cost modeling for inference workloads
Module 5: Security, Compliance, & Access Control • IAM, network isolation, protecting data, model & prompt security • Regulatory concerns (GDPR, HIPAA, etc.), audit, logging • Threat models specific to AI (e.g. model theft, prompt misuse). Threats: model inversion, data exfiltration, prompt injection • Zero-trust design for AI services
Module 6: Hybrid & Agentic AI, Future Trends • Architecting agentic AI systems • Hybrid & edge deployments • Patterns for evolution: experimentation → production – AWS Bedrock AgentCore, Agentforce, orchestration patterns (Supervisor, Pub/Sub, Router) – Edge inference trade-offs: latency vs cost vs control – Governance for multi-agent systems (auditability, rollback) – Future of WA: AI lifecycle management across frameworks
About Rohit Bhardwaj
Rohit Bhardwaj is Director of AI & Data Architecture at Salesforce, an O’Reilly instructor, and founder of AI Architect Circle. With 30 years of experience in software and enterprise architecture, he helps engineers, architects, and technology leaders make architecture decisions they can explain and defend.
His work brings together enterprise AI, agentic systems, data architecture, and distributed systems. He focuses on the decisions that determine whether a system remains reliable, secure, accountable, and economically sustainable when it encounters real-world demands.
Rohit’s talks and workshops explore practical questions: What happens when an AI agent acts on conflicting information? Can a failed payment be retried safely? Who can stop an autonomous action, and what evidence explains the decision afterward? His teaching connects these questions to architecture, customer trust, and business outcomes.
He is the author of System Design with AI Interview Guide: Designing Scalable, Agentic, and Defensible Systems, published by Apress. He also developed ARCHVIEW™, ROCS Loops™, and LLM-SHIELD™ to help teams structure architectural thinking and address the challenges of building trustworthy AI systems.
Through AI Architect Circle, Rohit extends this learning through live discussions, book walkthroughs, videos, and interactive architecture challenges. These challenges explore incidents such as payment timeouts and conflicting bookings, helping participants practice the judgment behind their design decisions.
Continue learning with Rohit
Join Rohit live on Saturdays at 9:00 a.m. Eastern
System Design with AI — Live with the Author is a free live podcast and Q&A series featuring practical system-design scenarios, AI architecture discussions, and questions from the community.
See the next session and register
Try an interactive architecture challenge
Put your design decisions under pressure and explore the consequences.
Explore the challenges
Explore AI Architect Circle
Find architecture lessons, videos, resources, and ways to continue learning.
Visit AIArchitectCircle.com
Read the book: Amazon · O’Reilly
Watch and connect: YouTube · Instagram: @aiarchitectcircle · LinkedIn · X / Twitter: @rbhardwaj1
More About Rohit »