Master Thesis - AI - Driven RF Production Test Intelligence

• Join our Team

About this opportunity

This master-thesis will explore how AI and machine learning can transform large-scale RF production test data into actionable engineering insights. By correlating RF performance metrics with more factors, it aims to detect anomalies, support RCA, flag quality risks, and identify opportunities to optimize test coverage and time - helping engineers resolve issues faster and get higher quality products.

What you will do

This Master Thesis investigates the application of Artificial Intelligence and Machine Learning techniques on RF production test data from Ericsson radio products. You will have the opportunity to explore multiple aspects of data-driven production intelligence and define areas of focus together with supervisors.

Possible areas of investigation include, but are not limited to:

Production Data Understanding and Feature Engineering

Analyze large-scale RF production test datasets.

Identify key RF performance indicators and manufacturing parameters.

Develop methods for data cleansing, normalization, and feature extraction.

AI-Based Anomaly Detection

Investigate machine learning approaches for detecting abnormal test behavior.

Identify outlier devices and unusual production trends.

Compare conventional statistical methods with modern AI techniques.

Root Cause Analysis Support

Correlate RF test results with manufacturing information, component lots, test stations, environmental conditions, and other available factors.

Explore how AI can assist engineers in narrowing down potential root causes.

Develop explainable analysis methods to improve engineering confidence.

Production Quality Risk Prediction

Investigate predictive models for identifying potential quality risks before products leave manufacturing.

Study early indicators of future failures or yield degradation.

Evaluate model performance using historical production data.

Test Coverage Optimization

Analyze relationships between different production test steps.

Identify redundant measurements and opportunities to streamline testing.

Evaluate potential reductions in test time while maintaining product quality and fault coverage.

Data Visualization and Engineering Insights

Develop intuitive visualizations and dashboards for production data exploration.

Present AI-generated insights in a way that supports engineering decision-making.

Investigate techniques for explainable AI within a production environment.

Proof-of-Concept Implementation

Build and evaluate a proof-of-concept AI solution using real production data.

Demonstrate the ability to detect anomalies, provide engineering insights, and support production optimization activities.

Assess deployment opportunities and future industrial applications.

The skills you bring

Knowledge in Computer Science, Electrical Engineering, or a related field.

Knowledge of data visualization and statistical analysis.

Familiarity with RF systems, wireless communication, electronics, or manufacturing processes.

Experience in at least one programming language (Python not mandatory).

Eagerness to learn and explore new concepts.

Bonus: experience in machine learning.

Why join Ericsson?At Ericsson, you´ll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what´s possible. To build solutions never seen before to some of the world's toughest problems. You´ll be challenged, but you won't be alone. You´ll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.

Primary country and city: Sweden (SE) || Lund

Req ID: 790711