• Build, run, and evolve production ML and LLM systems by implementing feature pipelines, training and retraining workflows, and batch and real-time inference on top of Qventus’ data platform • Monitor and optimize model performance across hospitals, improving accuracy, latency, cost, and reliability • Build and maintain model-level feature pipelines and feature management systems on top of curated datasets to support training, inference, and replay. • Collaborate with Data Science leaders to establish best practices for applied ML at Qventus, setting standards for feature design, evaluation, and production readiness through iteration and retraining