Qeexo AutoML B2B SaaS

Product Overview

Automated Machine Learning Platform

Qeexo’s AutoML platform is a fully-automated end-to-end machine learning solution, allowing customers to collect, clean and visualize sensor data on their own to rapidly build machine learning solutions for highly constrained environments with applications in mobile, IoT, wearables, automotive, and more. 

Design Process

Defining a Creative Strategy

The project originated from the collaborative efforts of the engineering team, spearheaded by their innovative approach. Initially, a basic software solution was crafted to lay the foundation for further development and refinement.

Implementation

Foundational Flow

Step 1: Define Project

Choose what type of machine learning best fits the problem at hand.

Step 2: Select Sensors and Target Hardware

Select a supported hardware module to see its sensors and their capabilities. Handpick the most relevant sensors or select them all let AutoML do the vetting.

Step 3: Collect/Upload Data

Intuitive UI is provided for users to easily collect, upload, and visualize sensor data.

Step 4: Automated Machine Learning and Deploy/Download ML Package

Select the model that best fits the needs of the project and deploy it onto the target embedded device with just one click.

Additional Product Screens

My Role

Created user-centered solutions for Qeexo’s AutoML platform, a tool used by machine learning engineers to train, evaluate, and deploy deep learning models to edge devices. My focus was on simplifying complex workflows into intuitive UI patterns that made model training and deployment accessible – even to users without extensive data science backgrounds. Working closely with product managers and engineers, I translated technical requirements into clean, usable interfaces, ensuring clarity at every stage of the machine learning pipeline. This included designing for advanced capabilities like model comparison, sensor data visualization, and real-time performance monitoring, while maintaining consistency and usability across the platform.

Year: 2019-2020

OS: Desktop