Context. Modern software systems increasingly commonly contain one or multiple machine learning (ML) components. However, current development practices are generally ad hoc, on a trial-and-error basis, introducing a significant risk of introducing bugs. One interesting type of bug is the “conceptual design bug,” which arises when a ML engineer misunderstands the compatibility between their dataset, the ML algorithms they use, and the hyperparameters they use to tune it; i.e., they misunderstand these components at a conceptual level, affecting the system’s design. These bugs are challenging to test at design time, as the code is generally syntactically correct and problems only arise at runtime through crashes, noticeably poor model performance, or not at all, threatening the system’s robustness and transparency. Objective. In this work, I propose the line of research I intend to pursue during my PhD research, addressing conceptual design bugs in complex ML software from a prevention-oriented perspective. We intend to build open-source tooling for ML engineers that can be used to detect conceptual design bugs, enabling them to make quality assurances about their system design’s robustness. Approach. We need to understand conceptual bugs beyond the status quo, identifying their types, prevalence, impacts, and structural elements in the code. We operationalize this knowledge into a tool that detects them at design time, allowing ML engineers to resolve them before running their code and wasting resources. We anticipate this tool to leverage two known model-driven techniques: “contract-based validation” and “partial model checking.” Evaluation. We plan to evaluate the built tool two-fold using professional (industrial) ML software. First, we will study its effectiveness regarding bug detection at design time, identifying whether it fulfills its technical objective. Second, we will study its usability, identifying whether ML engineers benefit when tools like this are introduced into their ML engineering workflow.