INDIVIDUAL LEARNERS

SCHOOL OF ARTIFICIAL INTELLIGENCE

AI Engineer using
Microsoft Azure
Nanodegree Program Syllabus
Overview
This program will equip learners with the skills required to become an Azure AI engineer or an AI engineer with expertise in
Azure AI and machine learning services. It will teach learners how to implement machine learning models, design and build
an end-to-end AI solution with Azure Cognitive Services, and deploy, monitor, and manage continuous improvement of an
Azure AI solution. Learners seeking certification who successfully complete this program are ideal candidates for Microsoft
certification A1-102.

Learning Objectives

A graduate of this program will be able to:

• Design and build an end-to-end AI solution with Azure Cognitive Services/Azure Cognitive APIs.

• Design a security strategy that aligns with organizational policies and compliance frameworks.

• Deploy, monitor, and manage continuous improvement of an Azure AI solution.

Built in collaboration with:

AI Engineer using Microsoft Azure 2

Program information

Estimated Time Skill Level

3 months at 10hrs/week* Advanced

Prerequisites

A well-prepared learner should have the following Python programming skills:

• Understanding the basics of object-oriented programming.

• Reading basic Python syntax, including using white space in Python.

• Distinguishing between object types like integers and strings in scripts.

• Using Python to build basic algorithms for simple programs and scripts that automate common tasks (i.e. renaming files).

• Writing and running basic programming scripts in a terminal that includes function definitions and loops.

Learners should also have:

• Knowledge of Microsoft Azure and the ability to navigate the Azure portal.

• Familiarity with a variety of Azure data sources such as Azure Data Lake and Azure SQL.

• Knowledge of JSON and REST programming semantics and the ability to use APIs in application development.

AI Engineer using Microsoft Azure 3

 Required Hardware/Software

Learners need access to:

• Azure Portal (Browser based)

• VS Code

• Microsoft Bot Framework Emulator

• Node.js V16

• Python 3.6 and above

• Various Azure cognitive Services SDK (Python)

*The length of this program is an estimation of total hours the average student may take to complete all required
coursework, including lecture and project time. If you spend about 5-10 hours per week working through the program, you
should finish within the time provided. Actual hours may vary.

AI Engineer using Microsoft Azure 4

 Course 1

Building Computer Vision Solutions with Azure

This course is designed for anyone who would like to use computer vision technology in their application to solve a business
problem. Learners will begin by finding out what computer vision is and and how it works through real-life business use cases.
They will then learn to create solutions using different types of vision-based Azure Cognitive Services, including Azure Form
Recognizer for text extraction, Azure Face and Video Analyzer for facial detection and recognition, and Azure computer vision
and Custom Vision for image classification and object detection. Finally, they will learn and apply deployment and monitoring
tools to ensure that their solution is complete and runs smoothly.

Course Project

Automated Passenger Boarding Kiosk

Build an automated passenger boarding kiosk to collect passenger and flight information through the
passenger’s face image, digital ID, boarding pass, etc. Perform various validation processes and confirm if a
given passenger can board the plane or not. Use various Azure Cognitive Services and supporting services
for this project, including Azure computer vision, Face, Form Recognizer, Video Analyzer, Azure Blob Storage
in a Python run-time environment.

• Identify business and technical considerations for creating computer vision

Lesson 1 applications.

• Identify data considerations and sources for Azure computer vision solutions.
Design Computer
Vision Applications • Identify various Azure computer vision services for a given business scenario.

• Identify various programming models to use with Azure Cognitive Services.

AI Engineer using Microsoft Azure 5

 • Apply the prebuilt layout recognizer and create a custom layout recognizer
model to extract the layout of a digital document.
Lesson 2
• Apply the prebuilt Azure Form Recognizer service to read the text from images
Extracting Text from and documents.
Digital Content
• Create a custom form recognizer model to collect text data from a digital
document.

• Understand the terms involved in face detection and recognition.

Lesson 3
• Identify face(s) in an image or a collection of images.
Facial Detection • Create a custom face recognition model to identify a person’s face.
& Recognition
• Process faces in a video using Azure Video Analyzer.

• Apply image classification and object detection concepts.

Lesson 4
• Learn binary and multi-class classification and multi-label image classification.
Image Classification
• Create a custom image classification model to classify your own images.

Lesson 5 • Learn object detection concepts.

• Create a custom object detection model to identify a specific object.

Object Detection &
Spatial Analysis • Understand the basics of spatial analysis.

• Understand and apply computer vision solution deployment, accessibility, and

Lesson 6 security.

• Understand and apply application monitoring with extended logging and

Solutions Deployment
enhanced diagnostics.
& Monitoring
• Export and delete data and models with cost management.

AI Engineer using Microsoft Azure 6

 Course 2

Building NLP & Conversational AI Solutions

with Azure
Learn how to build conversational AI and NLP solutions on Azure. Explore use cases including chatbots and assistant solutions,
then create solution diagrams, model dialogs, and learn about responsible AI principles and practice creating requirements.
Learners will also create and configure bot applications and implement Azure Text and Speech Cognitive Services in
applications.

Course Project

Dental Office Virtual Assistant

Create a customer support chatbot for a dentist website using the Azure platform, a Node.js bot application,
and a LUIS model and QnA knowledge base. The bot will use the Azure QnA knowledge base and LUIS to
answer patient questions and help them schedule appointments. Deploy the bot application and resources
to Azure and implement the assistant in a website.

• Create requirements for NLP and conversational AI solutions including creating

user stories and dialog modeling.
Lesson 1
• Create architecture diagrams based on the components of Azure NLP and
Designing NLP & cognitive services.
Conversational AI Solutions
• Implement responsible AI use of Azure Text Analytics, QnA Maker, and Speech
Services.

AI Engineer using Microsoft Azure 7

 • Create and configure bot resources for chatbot and assistant applications on
Azure.

• Create Node.js bot applications using the Microsoft Bot Framework SDK and
Lesson 2 templates.

• Identify the components of a bot framework application including context,

Building Bots with the Bot
dialog, and adapters.
Framework
• Test Microsoft Bot Framework applications using the Bot Framework Emulator.

• Configure and deploy bot applications on Azure using Github continuous

integration and deployment.

• Use Azure Language Understanding Service (LUIS) to identify intents and

entities in the context of conversational AI solutions.
Lesson 3 • Define and train language understanding models with Azure LUIS service.

NLP Cognitive • Use Azure QnA to identify intent in the context of conversational AI solutions.

• Create QnA knowledge bases.

Services
• Implement Language Understanding Services (LUIS) and QnA knowledge bases
in conversational AI applications.

• Identify and extract entities and key phrases from text using Azure text
Lesson 4 analytics.

• Extract phrases and run sentiments analysis on text using Azure text analytics.
Text Analytics &
Speech Services • Speech enable a bot application with Azure Cognitive Speech Services and bot
channels.

AI Engineer using Microsoft Azure 8

 Course 3

Building Knowledge Mining Solutions with Azure

Cognitive Search
This course addresses the skills necessary to design and implement an Azure Cognitive Search solution for knowledge mining.
In this course, learners will add data sources to Azure Cognitive Search, enrich the data with AI, properly index the enriched
data, and expose the index to client applications for search scenarios. They will begin by learning how to design an Azure
Cognitive Search solution and finish the course by building out an AI-enriched data mining application from end to end.

Course Project

Build an AI Enriched Corporate Training Catalog

Create a knowledge-mining solution to help employees gain insights into training materials made available
by their company. Learners will combine 4 datasets: a set of Udacity courses, a set of Microsoft Learn
courses, a generated set of corporate training, and a set of open-source papers. They will enrich these data
using built-in skills such as OCR, key phrase extraction, and custom entity recognition, as well as a custom
skill. Learners will connect a user-facing search interface to this solution and demonstrate various query
capabilities of the solution.

Lesson 1 • Create a list of requirements that match various business needs.

Designing & Azure Cognitive • Create a high-level architecture diagram based on the available components of

Search Solution Azure Cognitive Search.

AI Engineer using Microsoft Azure 9

 • Import data from different types of sources using the Azure Portal wizard.

• Implement enrichments such as document cracking and text analysis during

data import.

• Configure and customize indices to utilize different features of Azure Cognitive

Lesson 2
Search.
Importing Data into Azure • Create and schedule an indexer to populate indexes.
Cognitive Search
• Create different types of search queries using correct syntax such as basic,
semantic, and fuzzy searching.

• Create properly formed search queries to utilize the range of functionality

available in Azure Cognitive Search such as ordering, filtering, and faceting.

Lesson 3
• Fully configure built-in Azure Cognitive Search skills including updating the
Enriching Data in Azure skillset definition, the indexes, and the indexer.
Cognitive Search

• Configure a stand-alone search application to securely connect to Azure

Lesson 4
Cognitive Search utilizing the search query endpoints.
Consuming Azure Cognitive • Monitor and report on usage metrics such as storage used, number of indices,
Search in an External indexers, and data sources, as well as monitoring metrics such as search
Application latency and queries per second.

AI Engineer using Microsoft Azure 10

Meet your instructors.

Avkash Chauhan
Founder & Principal at UnBlocker.ai

Avkash Chauhan has over 20 years of software development experience including the last
10 years building AI and ML platforms and solutions for enterprise customers. His previous
work experience includes Microsoft, H2O.ai, Macnica, RoamBee and his own startups Big Data
Perspective and UnBlocker.ai.

Valerie Scarlata
Curriculum Manager at Udacity

Valerie is a curriculum manager at Udacity who has developed and taught a broad range of
computing curriculum for several colleges and universities. She was a professor and software
engineer for over 10 years specializing in web, mobile, voice assistant, and social full-stack
application development.

Matt Swaffer
Solutions Architect

Matt is a software and solutions architect focusing on data science and analytics for managed
business solutions. In addition, Matt is an adjunct lecturer, teaching courses in the computer
information systems department at the University of Northern Colorado where he received his PhD
in educational psychology.

AI Engineer using Microsoft Azure 11

Udacity’s learning
experience

Hands-on Projects Quizzes

Open-ended, experiential projects are designed Auto-graded quizzes strengthen comprehension.
to reflect actual workplace challenges. They aren’t Learners can return to lessons at any time during
just multiple choice questions or step-by-step the course to refresh concepts.
guides, but instead require critical thinking.

Knowledge Custom Study Plans

Find answers to your questions with Knowledge, Create a personalized study plan that fits your
our proprietary wiki. Search questions asked by individual needs. Utilize this plan to keep track of
other students, connect with technical mentors, movement toward your overall goal.
and discover how to solve the challenges that
you encounter.

Workspaces Progress Tracker

See your code in action. Check the output and Take advantage of milestone reminders to stay
quality of your code by running it on interactive on schedule and complete your program.
workspaces that are integrated into the platform.

AI Engineer using Microsoft Azure 12

Our proven approach for building
job-ready digital skills.
Experienced Project Reviewers

Verify skills mastery.

• Personalized project feedback and critique includes line-by-line code review from
skilled practitioners with an average turnaround time of 1.1 hours.

• Project review cycle creates a feedback loop with multiple opportunities for
improvement—until the concept is mastered.

• Project reviewers leverage industry best practices and provide pro tips.

Technical Mentor Support

24/7 support unblocks learning.

• Learning accelerates as skilled mentors identify areas of achievement and potential
for growth.

• Unlimited access to mentors means help arrives when it’s needed most.

• 2 hr or less average question response time assures that skills development stays on track.

Personal Career Services

Empower job-readiness.
• Access to a Github portfolio review that can give you an edge by highlighting your
strengths, and demonstrating your value to employers.*

• Get help optimizing your LinkedIn and establishing your personal brand so your profile
ranks higher in searches by recruiters and hiring managers.

Mentor Network

Highly vetted for effectiveness.

• Mentors must complete a 5-step hiring process to join Udacity’s selective network.

• After passing an objective and situational assessment, mentors must demonstrate

communication and behavioral fit for a mentorship role.

• Mentors work across more than 30 different industries and often complete a Nanodegree
program themselves.

*Applies to select Nanodegree programs only.

AI Engineer using Microsoft Azure 13

Learn more at
www.udacity.com/online-learning-for-individuals →

01.13.23 | V1.0