Build With LLMs: From Context Engineering to Multi-Agent Systems

Modern LLM Systems & AI Applications

  • Attend live online sessions led by CMU School of Computer Science faculty
  • Design, evaluate, and secure reliable LLM-powered systems
  • Engineer RAG, tool calling, and multi-agent AI workflows
  • Build production-ready applications powered by modern LLMs

Talk to an advisor :

+1-844-532-7688
Build With LLMs: From Context Engineering to Multi-Agent Systems
Ranked #1 in the U.S.

Talk to an advisor :

+1-844-532-7688
  • Admission closes
    September 26, 2026
  • Program Duration
    8 weeks
  • Learning Format
    Live, Online, Interactive

Key Features

CMU Credential

Earn a certificate of completion from CMU School of Computer Science Executive Education

Curriculum designed and delivered by CMU School of Computer Science faculty

Technical Foundations

Trace LLM evolution from word embeddings via transformers to frontier models

Explore self-attention, BERT, in-context learning, and modern training approaches

Applied LLM Engineering

Build RAG pipelines with retrieval, embeddings, chunking, and vector databases

Design tool integrations using tool calling, permissions, APIs, and MCP

Need to know more?

+1

Need to know more?

Talk to an Advisor

Toll Free : +1-844-532-7688

Corporate Training

Enroll your employees into this program, NOW.

Corporate training

Talk to an Advisor

Toll Free : +1-844-532-7688

Career Opportunities

AI / LLM Engineer

Builds production-ready LLM applications using context engineering, RAG pipelines, and evaluation guardrails. Develops scalable solutions that integrate LLMs with enterprise data, APIs, and workflows.

Source: Glassdoor

Hiring Companies
Average Salary

Essential Skills You Will Develop

  • Multi Agent Systems
  • AI Safety
  • Chain of Thought Prompting
  • Context Engineering
  • Embeddings
  • In Context Learning
  • LLM Evaluation
  • Retrieval Augmented Generation
  • Vector Databases
  • Model Context Protocol
  • Large Language Models
  • Prompt Engineering
  • Tool Calling

Earn Professional Certifications

Upon successful completion, earn a digital certificate from Carnegie Mellon University School of Computer Science Executive Education - validating your expertise in building production-grade LLM and Agentic AI systems.

The U.S. News & World Report Ranks CMU
The U.S. News & World Report Ranks CMU
  • #1 in Artificial Intelligence programs
  • #1 in Programming Language and Systems
  • #1 for overall graduate computer science programs

Program Curriculum

Take your LLM skills from foundations to building reliable AI applications. Explore context engineering, reasoning, RAG, tool integration, multi-agent systems, and AI safety while developing and evaluating real-world LLM solutions.

  • Program Induction - Build With LLMs
    You will be introduced to the program and learning journey through a program overview.
  • Foundations of Large Language Models
    Explore the evolution of language models from embeddings to transformers, BERT, GPT, T5 and GPT-3. Understand pre-training data, corpora and data controversies. Examine benchmarks, contamination, scaling laws and emergent abilities. Explore the modern landscape of multimodal, reasoning, small, and open models, as well as MoE. Learn instruction tuning essentials, including FLAN and Self-Instruct, in a condensed format.
  • In-context Learning and Reasoning - CoT to Reasoning Models
    Learn prompt engineering fundamentals through instructions, templates, demonstrations, selection and order. Explore ICL, prompt sensitivity, biases, calibration and experiment design. Cover few-shot and zero-shot CoT, triggers, self-consistency and Auto-CoT, along with CoT limits and faithfulness. Learn Self-Ask, Plan-and-Solve, Step-Back, Tree/Graph-of-Thoughts and how reasoning models (o1/R1-class) are trained, including overthinking.
  • Augmentation: RAG, Tool Calling and MCP
    Learn RAG fundamentals including chunking, vectorization and similarity. Explore RAG limits, lost-in-the-middle and RAG vs long-context. Cover advanced chunking, embeddings and vector databases in practice. Learn tool-use foundations, tool evaluation and function calling mechanics. Explore web agents and Model Context Protocol (MCP), including architecture, servers and integrations.
  • Multi-Stage Pipelines & Self-Verification
    Explore task decomposition and prompt chaining with DecomP and Least-to-Most. Get an introduction to LangChain. Learn auto-prompting with APE, self-correction pitfalls and Chain-of-Verification. Understand LLM-as-a-Judge evaluation and its biases.
  • Agentic AI - Agents, Memory & Collaboration
    Explore agent fundamentals with ReAct, Reflexion and the TAO loop. Learn about agent memory systems and frameworks such as AutoGen and AgentKit. Understand planning challenges with LLM-Modulo and TravelPlanner. Explore multi-agent collaboration, debate and Mixture-of-Agents. Examine agent failure modes and modern frameworks including LangGraph and CrewAI.
  • Reliability & Alignment
    Understand hallucinations, including types, sources, calibration and mitigation. Explore bias, toxicity, fairness metrics and detoxification. Learn about sycophancy and the RLHF/InstructGPT pipeline. Examine ethics, deception and Sleeper Agents through condensed highlights.
  • LLM Security
    Explore prompt injection, including direct and indirect attacks and their mechanics. Learn about jailbreaking families, real-world attack case studies and key defenses such as guard models, firewalls and detection. Cover the OWASP LLM Top 10, data poisoning and model theft. Apply production guardrails in a hands-on NeMo/LlamaGuard implementation lab.
  • AI for Software Engineering
    Covers code generation evaluation and SWE agents like SWE-bench and OpenHands. Includes hands-on work with coding agents and examines the trade-off between development velocity and technical debt.
  • Build with LLMs Capstone Project
    Design and build an agentic LLM system combining RAG with MCP-based tools. Apply task decomposition, self-reflection, and orchestration; then evaluate faithfulness, tool correctness, sycophancy, and jailbreak resistance, and present your findings alongside mitigation strategies.

17+ Tools Covered

CMU-OpenAI
CMU-Deepseek
CMU-OLLAMA
AIML_Chroma
CMU-crew
AIML_LangChain
AIML_GitHub
AIML_Hugging Face
CMU-Perspective
CMU-Langgraph
CMU-Pypdf
CMU-BBQ
CMU-MCP
CMU-Ragas
CMU-Selfcheck
CMU-SENTENCE
CMU-Tiktoken

Projects Covered

  • MCP Powered Order Assistant with Human Approval

    Build an MCP server that connects an AI assistant to order, returns and shipping tools, with human approval, audit logging and failure handling.

    MCP Powered Order Assistant with Human Approval
  • Multi Agent RFP Response System

    Orchestrate three specialized agents to extract RFP requirements, draft evidence-based responses and red-team claims using LangGraph or CrewAI.

    Multi Agent RFP Response System
  • Secure an AI Copilot Through Red Teaming

    Red-team an AI copilot using prompt injection, strengthen it with guardrails, and measure improvements in its resilience through before-and-after security scans.

    Secure an AI Copilot Through Red Teaming
  • Secure RAG Powered AI Agent

    Develop a RAG agent that answers from trusted documents, then test it against prompt injection and strengthen its resilience with security guardrails.

    Secure RAG Powered AI Agent
  • AI Assistant for Small Business Support

    Create an AI assistant grounded in SBA and IRS guidance that answers business queries and takes action through an appointment-booking tool.

    AI Assistant for Small Business Support
  • AI Powered IT and HR Helpdesk

    Design an internal helpdesk assistant that retrieves relevant information, answers employee queries and creates support tickets with human approval.

    AI Powered IT and HR Helpdesk
  • AI Assistant for Campus Policy Support

    Develop an AI assistant grounded in CMU academic policies to provide reliable, policy-based answers and support informed decision-making.

    AI Assistant for Campus Policy Support
  • Advanced Context Engineering for Coding Agents

    Apply context engineering to help coding agents tackle complex production codebases using compaction, sub-agents, re-steering, and structured research and implementation workflows.

    Advanced Context Engineering for Coding Agents
  • Context Engineering for Effective AI Agents

    Explore how to manage context for AI agents through system prompts, tool selection, retrieval, compaction, and long-horizon memory to improve agent reliability.

    Context Engineering for Effective AI Agents
  • Securing AI Agents in Production Lessons from Replit

    Examine the Replit database incident and identify controls for safer AI agents, including IAM restrictions, approval gates, sandboxing, backups, monitoring, and policy-as-code.

    Securing AI Agents in Production Lessons from Replit

Program Faculty

  • Travis D. Breaux

    Travis D. Breaux

    Associate Professor of Computer Science, Carnegie Mellon University

    A leading researcher in AI, privacy, and software engineering, Professor Travis D. Breaux specializes in trustworthy AI, LLM-powered systems, and secure, policy-compliant software design.

Still have questions?

Our dedicated team is prepared to answer them.

Total Program Fee

Program Fee $ 4,000
11% off

$ 4,500

Pay in Installments

You can pay monthly installments using our payment partners with low APR and no hidden fees.

Program Cohorts

  • Limited seats Left

    CMU Build With LLMs: From Context Engineering to Multi-Agent Systems Nov 2026

    • cohort date05 Nov, 2026 - 11 Feb, 2027
    • cohort calendarWeekdayMTuWThFSaSu
    • cohort clock17:00 - 18:30 CST
    • InductionInduction on 28 Oct, 2026

Who Is This Program For?

Eligible student for this program
  • AI and ML professionals
  • LLM application professionals
  • Software engineers and developers
  • AI systems engineers
  • AI application engineers

Eligibility Criteria

  • Functional knowledge of Python programming
  • Familiarity with machine learning and LLM concepts
  • 3+ years of work experience in IT or technology roles

How To Apply

  • 1
    Submit Application

    Submit your online application

  • 2
    Reserve Your Seat

    Pay the program fees to complete your enrollment

  • 3
    Start Learning

    Congratulations! You are now enrolled into the program

Start Application

+1

Demand For Program

Large language models are evolving from standalone text-generation tools into systems that can reason, retrieve external knowledge, use tools, and coordinate agents. Building these systems requires engineering fluency across context engineering, in-context learning, reasoning, retrieval, tool integration, agent orchestration, and AI safety.

This program addresses that progression, from foundational LLM architectures to advanced applications. You'll explore how to guide models through context and demonstrations, apply reasoning techniques, ground outputs through RAG, connect models to external systems using MCP, and design autonomous and multi-agent workflows. The program culminates in a capstone where you'll build and evaluate an agentic LLM system against defined measures of reliability, tool correctness, sycophancy, and resistance.

Demand For Program

Growing demand

Program FAQs

About Carnegie Mellon University