Generative AI Engineering & Systems Strategy

Register Here

Build the skills to engineer, evaluate, and deploy generative AI systems.

Earn an accelerated Badge in Generative AI Engineering & Systems Strategy in 3 weeks: October 6 - 24

Building production-ready AI systems requires engineers to understand what happens underneath the API, from foundation models and retrieval to evaluation, deployment, monitoring, and responsible AI.

This accelerated badge gives engineers a condensed, end-to-end view of the generative AI engineering lifecycle. Through technical instruction and hands-on labs, you’ll build the knowledge and intuition to make better architecture decisions, prototype GenAI systems, evaluate their performance, and understand what it takes to operate them in production.
 

What you'll be able to do

By the end of the badge, you will be able to:

• Understand how modern LLMs work, from pretraining and instruction tuning to token generation and inference.
• Design reliable LLM interactions using prompting, structured outputs, validation, and retry strategies.
• Choose the right GenAI approach—prompting, RAG, fine-tuning, or agentic systems—based on the problem, data, cost, latency, and reliability requirements.
• Build RAG systems that retrieve and ground responses in private or up-to-date information.
• Fine-tune LLMs using supervised fine-tuning and parameter-efficient techniques such as LoRA, and evaluate whether fine-tuning actually improves the target behavior.
• Design tool-using and agentic systems using tool calling, workflows, planning, state, memory, and MCP—and recognize when an agent is unnecessary.
• Evaluate GenAI systems systematically, using representative test sets, task-specific metrics, rubrics, human evaluation, and LLM-as-judge.
• Diagnose common GenAI failure modes such as hallucination, inconsistency, brittle behavior, retrieval failures, and unreliable tool use.
• Understand and optimize LLM inference, including prefill and decode, KV caching, decoding strategies, quantization, acceleration, and model routing.
• Build and present a functional GenAI prototype, and justify its architecture and engineering tradeoffs.
• Apply AI governance principles to engineering and organizational decisions.
• Identify engineers' responsibilities around privacy, accountability, and responsible AI.

Co-developed and co-taught by Dr. Mina Ghashami, a Senior Machine Learning Engineer at Meta with deep hands-on experience building and deploying LLM-powered systems, and Prof. Julia Stoyanovich, a leading researcher in responsible AI, founding director of the NYU Center for Responsible AI, and Associate Dean of AI Initiatives at NYU Tandon.

Built for engineers who are building AI systems

This badge is designed for technical practitioners who already understand software, data, infrastructure, or machine learning and need to apply that expertise to generative AI.

Engineers transitioning into AI work

• Software engineers (backend, full-stack) at companies that are now building AI features
• Data engineers who work with pipelines but haven't built LLM-powered systems
• DevOps and platform engineers moving toward MLOps
• API/integration developers who connect to AI services but don't yet understand what's underneath

Technical roles adjacent to AI teams

• Technical product managers on AI product teams
• Solutions architects at companies deploying AI for clients
• Developer advocates and technical evangelists at AI-adjacent companies
• Technical consultants advising organizations on AI adoption

Practitioners broadening their skills

• Data scientists from traditional ML/analytics who want to move into GenAI engineering
• Research engineers transitioning from academic or R&D settings into production roles
• AI engineers at companies whose current work is narrow (e.g., only prompting, or only fine-tuning) who want the full picture

Engineering leadership who need technical depth

• Engineering managers overseeing AI teams who need to make credible technical decisions
• CTOs and VPs of Engineering at startups and mid-size companies building AI products
• Staff engineers and technical leads designing systems that incorporate AI components
   

Course Schedule