Edge Machine Learning Engineer roadmap › Courses

Best courses for Edge Machine Learning Engineers

This list covers the courses for putting models on devices: the runtimes that run them, the tools that shrink them, and the hardware guidance you need once you know the target chip.

Every course here is free and published by the runtime or framework team, so the cost is the hardware you test on. The runtime you pick depends on the device and the framework your model was trained in.

Convert one model with each runtime you list, measure it on a real device, and record the latency and memory. That measured comparison is the skill this role is hired for.

  • 6 items in 3 stages: 6 courses and tutorials, 0 certifications.
  • We opened every page on November 20, 2026 and show only what the provider states.
  • No prices, ratings or enrollment counts.

See the full Edge Machine Learning Engineer roadmap →Best books for Edge Machine Learning Engineers →

How to choose your courses

A short method, so you spend your hours on the right thing for where you are instead of collecting certificates.

Find your stage

  • Getting started · 1 items

    The on-device runtime path. Start with the current official guide to shipping a model to a device, and read it before you choose a runtime.

    Jump to this stage ↓
  • Doing the job · 4 items

    The conversion and optimization layer: the cross-platform runtime, the on-device path for PyTorch models, and the two quantization toolkits.

    Jump to this stage ↓
  • Senior and leading · 1 items

    Hardware-specific guidance. Read it once you know which chip and operating system the product will use.

    Jump to this stage ↓

If you are unsure, start one stage lower than you think. Later items assume what the earlier ones teach.

Begin with one course

Our starting pick

LiteRT: High-Performance On-Device Machine Learning Framework

Google AI Edge

It is the official path for shipping a model to a phone or embedded device, and it names the three steps you will repeat on every model: convert, quantize, and deploy.

See the course ↓

Then pick by your situation

Choose the next course by the problem in front of you, not by its place in the list.

Free path or paid path?

5 of the 6 courses and tutorials can be read or taken without paying, so you can build most of the skill at no cost. Check each certification page for exam fees.

Paid courses earn their place when you need structure, deadlines or feedback. Check what the provider says is included before you commit.

Judge any course before you commit

  • Who runs it

    Prefer courses from the people who build or govern the tool. They tend to stay current, and an exam from a tool’s own maker is the clearest credential for that tool.

  • Hands-on or watch-only

    In this field you learn by running things. Choose material where you build a pipeline, a cluster or a dashboard over material you only watch.

  • How current it is

    Tools change fast. Look for a version or last-updated date on the provider’s page, and check anything several years old against the current docs.

  • What you will be able to show

    Ask what you will have at the end: a working repository, a deployed service or a passed exam. If it is only a certificate of completion, pair it with a project of your own.

Getting started

The on-device runtime path. Start with the current official guide to shipping a model to a device, and read it before you choose a runtime.

  • Start hereHands-on tutorialFree to learn

    LiteRT: High-Performance On-Device Machine Learning Framework

    Google AI Edge

    View course →

    What you will learn

    • Convert models to the on-device format
    • Quantize models for a smaller size and faster inference
    • Deploy and accelerate on CPU, GPU and NPU

    Good for

    The current official path for shipping a model to a phone or embedded device.

    Also stated by the provider

    • Formerly TensorFlow Lite; the TensorFlow Lite guide URL redirects here

Doing the job

The conversion and optimization layer: the cross-platform runtime, the on-device path for PyTorch models, and the two quantization toolkits.

  • Hands-on tutorialFree to learn

    ONNX Runtime Tutorials

    ONNX Runtime

    View course →

    What you will learn

    • Deploy on mobile
    • Deploy on IoT and edge devices
    • Run models in the browser
    • On-device training

    Good for

    A cross-platform runtime, useful when the same model has to run on several kinds of device.

  • Hands-on tutorialFree to learn

    Getting Started with ExecuTorch

    PyTorch ExecuTorch

    View course →

    What you will learn

    • Export a PyTorch model for the target hardware
    • Run it with the ExecuTorch runtime
    • Deploy to the target platform

    Good for

    The on-device path for models you trained in PyTorch.

    Also stated by the provider

    • Installs the Python package and runtime libraries first
  • Hands-on tutorialFree to learn

    TensorFlow model optimization

    TensorFlow Model Optimization Toolkit

    View course →

    What you will learn

    • Quantization
    • Sparsity and pruning
    • Clustering

    Good for

    The toolkit for shrinking a model with a measured accuracy trade-off. Use it before you deploy a quantized model.

  • Hands-on tutorialFree to learn

    Quantization

    PyTorch

    View course →

    What you will learn

    • Eager mode quantization
    • FX graph mode quantization
    • PT2E quantization

    Good for

    The quantization modes for PyTorch models, from the simplest post-training path to the graph-based flows.

    Also stated by the provider

    • Documentation for PyTorch 2.15 at the time of reading

Senior and leading

Hardware-specific guidance. Read it once you know which chip and operating system the product will use.

  • Hands-on tutorial

    Arm Learning Paths

    Arm Developer

    View course →

    What you will learn

    • Embedded and microcontroller development
    • AI models on Arm-powered platforms
    • Optimizing Android apps

    Good for

    Hardware-specific guidance for the chips you will measure on. Read it once you know the target device.

    Also stated by the provider

    • Documentation under CC BY-SA 4.0 and sample code under BSD-3-Clause-Clear, as stated on the site

Details such as hours, format and whether material is free are as the providers state them on November 20, 2026, and can change. Confirm on the provider’s page before you commit. See our disclosure.

Frequently asked questions

Which course should a Edge Machine Learning Engineer take first?

LiteRT: High-Performance On-Device Machine Learning Framework, from Google AI Edge. It is the official path for shipping a model to a phone or embedded device, and it names the three steps you will repeat on every model: convert, quantize, and deploy.

Can a Edge Machine Learning Engineer learn this for free?

Largely, yes. 5 of the 6 courses and tutorials here can be read or taken without paying (LiteRT: High-Performance On-Device Machine Learning Framework, ONNX Runtime Tutorials, Getting Started with ExecuTorch, TensorFlow model optimization and more). Check each certification page for exam fees: not every page states one.

How was this list put together?

We opened each course, tutorial and certification page on November 20, 2026 and wrote down only what the page states: who runs it, what it covers, hours and exam format where given, and whether the material is free to read. We do not show prices, ratings or enrollment figures. Details can change, so confirm on the provider’s page before you commit.