High-performance computing (HPC) systems and their software stacks are not optimized for complex, dynamic workflows such as cosmology data pipelines and particle physics uncertainty quantification studies. Conversely HEP distributed workflow management systems are not optimized for execution on a single HPC system. The CCE Complex Workflows (CW) team will identify requirements for production and user-focused workflows, components, and execution environments. It will then develop HPC, container, and data scheduling models for improving performance in combination with node-level parallelization.