Summary
Bea Steers is a research scientist and data engineer with a decade of experience building data pipelines, visualizations, and machine learning systems in urban sensing environments. Based at NYU Center for Urban Science + Progress, she blends deep learning (TensorFlow) and classical ML to solve real-world problems like sensor fault detection and network monitoring for city-scale deployments. Her background in acoustical engineering and urban informatics informs nuanced approaches to audio-based models and low-latency dashboards, having slashed dashboard load times from ~10s to under 1s and migrated metrics to Grafana. Comfortable across Python and JavaScript, she bridges research and production, deploying models and alerting systems that keep sensor networks healthy. She also brings an experimental, research-minded perspective—balancing rigorous evaluation of many classifiers with pragmatic engineering to deliver operational solutions.
10 years of coding experience
B.S.E., Acoustical Engineering and Music, B.S.E., Acoustical Engineering and Music at University of Hartford
Master's degree, Urban Science & Informatics, Master's degree, Urban Science & Informatics at New York University