Contribution: This article contributes empirical insights on hybrid teaching of software engineering courses. Results include the systematic analysis of hybrid teaching attendance and interaction, perception of hybrid teaching, and grade distributions. Results are synthesized into eight evidence-based guidelines. Background: Hybrid teaching, i.e., teaching simultaneously to in-person and online students, is gaining an increasing adoption. However, how to improve the experience of students with respect to (w.r.t.) hybrid teaching is still an open question. Research Questions (RQs): How can the experience of students w.r.t. hybrid teaching be improved? RQ[subscript 1]: Are there differences between in-person and online student attendance and interaction? RQ[subscript 2]: What is the student perception of hybrid teaching? RQ[subscript 3]: Is in-person and online supervision influencing grades of students? Methodology: A mixed-method empirical research process is used, by considering two Master courses in software engineering. The process leverages three data sources, namely, quantitative and qualitative data collected during lectures, a student survey, and student grades. Summary statistics, coding processes, and a statistical analysis are used to answer the RQs. Findings: Students prefer to attend more frequently online, as it provides (among other factors) flexibility and convenience, while coming at the cost of lower focus and interaction quality. Following in-person is statistically a better choice to gain a median grade, while following online can lead with more probability to a higher or lower grade. Various guidelines are presented, ranging from the hybrid classroom setup, to online student management, and course component design.