NewYork-Presbyterian Hospital - New York, NY
posted 5 months ago
NewYork-Presbyterian is at the forefront of innovation, merging world-class healthcare with advanced machine learning technologies. We are looking for a talented and motivated machine learning engineer to join our dynamic team. This role involves leveraging extensive clinical data resources to develop, validate, and deploy cutting-edge machine learning technology. The successful candidate will engage in projects such as natural language processing of clinical text for summarization and the testing and application of generative AI models to analyze and interpret complex healthcare data. In this position, you will collaborate closely with national leaders in machine learning for healthcare and be part of a multi-disciplinary team that includes clinicians, data scientists, software engineers, and data engineers. Together, you will create scalable, AI-driven solutions aimed at improving diagnosis, treatment planning, and overall patient care. Your responsibilities will include analyzing clinical text and other multi-modal datasets, designing and developing applicable AI solutions, and maintaining foundational models for clinical data. You will also fine-tune, evaluate, and optimize both foundational and bespoke AI models, while assisting in defining project milestones, deliverables, and timelines. As a machine learning engineer, you will take ownership of specific tasks and coordinate effectively across teams to achieve defined milestones. You will develop data pipelines to collect, clean, and preprocess data for model development, collaborating with subject matter experts to ensure accurate data definitions and validate the quality of all data endpoints. Continuous monitoring of model performance and refinement will be key to ensuring accuracy, reliability, and scalability. You will demonstrate proficiency in the end-to-end machine learning pipeline, from data ingestion and cleaning to experimenting with predictive models and deploying results. Additionally, you will be responsible for writing, validating, and executing code for modeling or analytical tasks using both cloud and local compute environments (CPU or GPU). Creating informative reports and data visualizations to summarize data and results will be essential, as will understanding and evaluating appropriate performance metrics. Active engagement in meetings with stakeholders and contributing to presentations or discussions of summary reports will also be part of your role. You will follow best practices in documentation, code repositories, containers/environments, and version control, ensuring that these practices are upheld and enforced. You will adhere to all institutional policies regarding the appropriate use and safeguarding of data, assist junior data scientists and ML engineers as needed, and manage multiple projects simultaneously, functioning effectively both independently and as part of a team. Staying abreast of innovative technologies and approaches relevant to data science, AI, NLP, and healthcare technology will be crucial to evaluate their applicability and fit for current projects. Finally, you will perform other special projects and duties as assigned.