# AI/ML developer workflow
Source: [https://docs.qualcomm.com/doc/80-70014-15B/topic/aiml-developer-workflow.html](https://docs.qualcomm.com/doc/80-70014-15B/topic/aiml-developer-workflow.html)
Join Megha Daga, Senior Director of Product Management at Qualcomm, in this training session focused on the Qualcomm Linux AI Developer Workflow.
This video is tailored for developers and professionals in the IoT sector who are keen to enhance their understanding and skills in deploying on-device AI solutions.
The AI/ML developer workflow on Qualcomm Linux has two major steps:
| Step 1
Compile and optimize a model |
Compile and optimize the model from the third-party AI framework to efficiently run on Qualcomm hardware. For example, a Tensorflow model can be exported to a TFLite model.
Optionally, quantize, fine-tune performance, and accuracy using hardware-specific customizations.
|
| --- | --- |
| Step 2:
Build an application to use the optimized model to run on device inference |
Integrate the AI model into the use case pipeline.
Cross-compile the application to generate an executable binary using dependent libraries.
|
Note: This information is also available in
[Simplified Chinese](https://docs.qualcomm.com/bundle/publicresource/topics/80-70014-15BY).
Last Published: Jan 21, 2026
[Next Topic
Overview](https://docs.qualcomm.com/bundle/publicresource/80-70014-15B/topics/offering.md)