Waystar is looking to establish and execute a data science strategy to evolve the Waystar AltitudeAI™ platform, aiming to solve critical challenges in healthcare revenue cycle management (RCM) by predicting, preventing, and automating workflows, ultimately reducing administrative burden and improving financial performance for healthcare providers.
Requirements
- Demonstrated experience and deep theoretical understanding of Foundation Models (e.g., LLMs, VLMs), including model selection, fine-tuning techniques (e.g., LoRA, QLoRA), Retrieval-Augmented Generation (RAG) implementation, and prompt engineering for generating accurate, context-aware outputs in a healthcare setting (e.g., summarizing policy documents, drafting claim appeal responses).
- Demonstrated expertise in advanced machine learning algorithms, including XGBoost, Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformer architectures.
- Deep familiarity with natural language processing (NLP) approaches, including concept extraction, human language understanding, and summarization—particularly in clinical and healthcare contexts.
- Working knowledge of Python, PyTorch, and TensorFlow for developing and scaling machine learning solutions.
- Deep, hands-on expertise in the full machine learning lifecycle. Proven experience with advanced techniques like Deep Learning, NLP/Generative AI, and predictive time-series modeling, specifically applied to financial, claims, or clinical data.
- Proven track record of successfully applying data science to both clinical and financial/RCM data (e.g., EHR data, claims, remittances) to drive measurable outcomes is preferred.
- Experience with cloud-native solutions (AWS, GCP) and distributed computing frameworks.
Responsibilities
- Develop and champion a comprehensive data science and ML strategy that directly translates into new product capabilities and significant business value for Waystar and its clients. Focus on using data to predict, prevent, and automate RCM workflows.
- Establish and steward a portfolio of model types (e.g., classification, regression, ranking, forecasting, NLP/LLMs, anomaly detection) that address both clinical and financial objectives
- Integrate heterogeneous model outputs (clinical insights, operational predictions, financial risk scores) into an integrated, governed enterprise data set that supports analytics, product experiences, and downstream decisioning.
- Spearhead the research and deployment of cutting-edge AI and Generative AI solutions (e.g., using LLMs for policy document interpretation, predictive modeling for claim denial rates, intelligent task prioritization) to create differentiated, proprietary technology.
- Define and enforce best practices for the entire machine learning lifecycle in a regulated environment, including robust model governance, versioning, continuous monitoring, and drift detection to ensure accuracy and compliance of all production models.
- Act as the ultimate technical authority on machine learning principles, statistical rigor, and large-scale data analysis within the company. Provide hands-on guidance on complex projects involving unstructured healthcare data.
- Direct the technical architecture and tools used for all data science initiatives, leveraging cloud-native solutions (AWS, GCP) and distributed computing frameworks to handle Waystar's massive, multi-petabyte datasets.
Other
- VP of Data Science, you will be a strategic and technical leader reporting directly to the SVP of Data Science + Analytics.
- This role demands a visionary who can lead a world-class team, driving innovation to solve the most critical challenges in healthcare revenue cycle management (RCM).
- Collaborate closely with product, engineering, and commercial leaders to embed data science and ML into core platform offerings, ensuring technical initiatives align with market needs and HIPAA/security compliance.
- Act as a thought leader with analysts, customers, and prospects; communicate our approach, differentiation, and evidence of impact.
- Attract, mentor, and scale a high-performing, geographically distributed team of Data Scientists and Machine Learning Engineers, fostering a culture of technical excellence, accountability, and continuous learning.
