Infineon Automates Semiconductor Testing with AI

Nominated for the AI Impact Award 2026 in the Production and Supply Chain category

Adrian Schmitt Infineon AI Impact Award Interview
30.03.2026 | Article

The AI Impact Award, presented by the German business newspaper manager magazin and Porsche Consulting, honors companies that successfully and effectively apply artificial intelligence in real-world practice. The award highlights solutions that create genuine economic and societal added value.  

Infineon has been nominated for the AI Impact Award 2026 in the Production and Supply Chain category, which recognizes solutions that make processes across manufacturing, logistics, and supply chains more efficient, secure, or sustainable. In a short interview, Adrian Schmid, Senior Manager Digital Engineering & Customer Solutions in Infineon’s Power & Sensor Systems division, explains the challenges his team faced, how the AI-based approach was developed, the results achieved to date – and how Infineon is systematically advancing digitalization in chip development and manufacturing.

 

Mr. Schmid, what are the biggest technical and organizational hurdles in developing complex semiconductor test programs?

Developing test programs for semiconductors is a highly complex and time-consuming process. Test engineers must take into account large volumes of specifications, documentation, and test-specific details – often across multiple test platforms. This results in long development cycles, a strong reliance on individual experts, and limited reusability of existing test programs. At the same time, product complexity and time pressure continue to increase. From an organizational perspective, the sheer number of teams, tools, and processes makes consistent standardization difficult. The outcome is a process that is critical to quality and time-to-market, yet remains a structural bottleneck. For a semiconductor manufacturer with stringent requirements for quality and reliability, test engineering is a key lever for delivering robust products while maintaining rapid market entry.

Ein Operator bestückt die Frontend Testanlage mit einem Loadboard bei Infineon

An operator loads a frontend test system with a load board – this is where Infineon’s AI-based test programs are first applied to physical semiconductor chips.

Ein Operator bestückt die Frontend Testanlage mit einem Loadboard bei Infineon
An operator loads a frontend test system with a load board – this is where Infineon’s AI-based test programs are first applied to physical semiconductor chips.

How did you go about building “GenAI for Test Engineering” in practice? What role did the interaction between generative AI and human expertise play in the development process?

From the outset, we pursued an iterative, application-driven development approach. We started with a clear target vision: test engineers should be able to automatically generate an initial, functional test code from structured specifications. To achieve this, we worked closely with domain experts to define a lightweight program skeleton, integrate relevant documentation, and embed the solution into existing development environments. The generative AI creates the initial code draft – while validation and optimization are deliberately carried out by our test experts. This “human-in-the-loop” principle ensures that results are transparent, robust, and ready for production use. The combination of AI-driven automation and human expertise makes the solution practical, scalable, and standardizable, while enabling seamless integration into existing workflows and toolchains.

 

What measurable impact has automated test code generation delivered so far – for example in terms of development time, quality, or reusability?

The results to date show a clear efficiency gain. The manual effort required to create initial test modules has been reduced by 20 to 50 percent, depending on the product group. Individual test modules, the building blocks of a test program, can now be created within minutes instead of several hours. At the same time, the AI-based approach produces more structured and consistent code, improving reusability and making subsequent optimization cycles easier. Greater standardization also enhances transparency and maintainability – key factors for long-term quality and stable production processes. In addition, the solution lays the foundation for future improvements, such as data-driven optimization of test sequences. Even today, “GenAI for Test Engineering” delivers measurable acceleration and quality gains across the entire development process.

Insights

Trends & Solutions

Circular Economy for Rare Earths

How recycling critical raw materials strengthens Europe’s industrial competitiveness

Innovation Park for Artificial Intelligence

Porsche Consulting is part of the IPAI in Heilbronn

Top Rankings for Porsche Consulting in 2026

Porsche Consulting listed among the best German management consultancies by the business magazine brand eins

Filter

Industries

Practices