Data and research software are central to scientific innovation. High-Performance Computing (HPC) facilities and Research Data Management (RDM) units already deliver the technical infrastructure and specialised training that academic and industrial communities depend on to engage with HPC at scale. Yet many domain scientists need foundational support before they are ready to make use of these specialised services. A new position paper calls for central Research Software Engineering (RSE) units in research institutions to bridge that gap, applying the same pooling logic in HPC and RDM units: shared expertise, mutualised costs, and clear career paths. RSE units act as catalysts in the digital transformation of academic research, supporting domain scientists in the initial porting of serial applications to parallel programming models, delivering targeted training to lower the barrier to entry into the HPC ecosystem, and sustaining the long-term maintenance and community-building activities required to safeguard the longevity of research software.