University-industry collaboration plays an important role in the success of R&D projects. One of the main challengesof university-industry collaboration is the identification of suitable partners. Due to the information asymmetry problem, it is difficult for companies to identify researchers from universities for collaboration on their R&D projects. Various expert recommendation systems (e.g., question responder recommenders and co-author recommenders) have been proposed, but they fail to characterize companies' needs in identifying suitable researchers. This paper proposes a context-aware researcher recommendation system to encourage university-industry collaboration on industrial R&D projects. The system has two modules: an offline preparation module and an online recommendation module. In the offline preparation module, candidate researchers are identified in advance to improve the efficiency of the context-aware recommendation. In the online recommendation module, contextual information (i.e., R&D projects) is captured from a social network platform, and then, candidate researchers are recommended based on a contextual trust analysis model, which combines the expertise relevance, quality, and trust relations of researchers to profile and evaluate candidate researchers for the R&D project collaboration. An offline experiment and a user study are conducted to evaluate the effectiveness of the proposedrecommendation system. The results show that the proposed method achieves better performance than the baseline methods.