Heterogeneous computing systems, integrating diverse processing units such as central processing units (CPUs),graphics processing units (GPUs), and field-programmable gate arrays (FPGAs), have emerged as dominantarchitectures for high-performance computing applications. However, effective workload characterization andtask scheduling remain critical challenges due to the complex interplay between diverse hardware capabilities anddynamic application requirements. This paper presents a novel framework leveraging contrastive learning (CL)for automated workload characterization and predictive scheduling in heterogeneous computing environments.Our approach employs self-supervised representation learning to extract meaningful workload features fromhistorical execution traces without requiring extensive labeled datasets. By maximizing agreement betweenaugmented views of similar workload patterns while maintaining separation from dissimilar patterns, the proposedcontrastive learning framework learns robust representations that capture essential workload characteristicsincluding resource utilization patterns, communication overhead, and computational intensity. These learnedrepresentations enable accurate prediction of task execution times across different processing units and facilitateintelligent scheduling decisions that optimize system throughput and resource utilization. Experimental evaluationon real-world heterogeneous computing workloads demonstrates that our contrastive learning-based approachachieves superior performance compared to traditional scheduling heuristics, reducing average task completiontime by 28% and improving resource utilization efficiency by 34%. The framework shows particular effectivenessin handling workload diversity and adapting to dynamic system conditions, making it suitable for productionheterogeneous computing clusters.