Data Scientist

Job Title Required Qualifications Bachelor's degree or equivalent experience in Data Science, Statistics, Computer Science, Engineering, Applied Mathematics, or a related quantitative field. 5+ years of professional experience beyond degree in data science, machine learning, advanced analytics, statistical modeling, or a related technical discipline. Experience developing machine learning or statistical solutions for complex, real-world business problems. Experience with techniques applicable to anomaly detection, pattern recognition, classification, clustering, time-series analysis, or predictive modeling. Proficiency in at least one programming language commonly used for data science and machine learning, such as Python, R, or SAS. Strong SQL skills and experience working with large relational or analytical data platforms. Experience using source control and collaborative software development practices. Experience developing reusable, maintainable analytical code rather than exclusively notebook-based or ad hoc analyses. Ability to communicate technical concepts, analytical findings, system behavior, and model limitations to both technical and non-technical stakeholders. Preferred Qualifications: Master's degree in a quantitative, computational, or engineering discipline. Experience working with healthcare data, including claims, clinical, member, provider, financial, or operational datasets. Hands-on experience developing anomaly detection or pattern recognition systems using supervised, semi-supervised, or unsupervised learning techniques. Experience with advanced modeling approaches such as ensemble methods, deep learning, graph analytics, natural language processing, embeddings, or large language models. Experience with CI/CD platforms and automated deployment workflows for analytical or machine learning applications. Familiarity with MLOps practices including model registries, experiment tracking, automated testing, model versioning, deployment strategies, monitoring, observability, and model lifecycle management. Experience with workflow and pipeline orchestration technologies used to automate data processing, model training, scoring, and deployment. Experience integrating machine learning or analytical services with other technology systems through APIs, services, event-driven processes, databases, or enterprise applications. Experience working in cloud-based analytics environments, particularly Azure and Snowflake. Familiarity with containerization, infrastructure automation, or modern software engineering practices used to deploy and operate analytical workloads. Experience troubleshooting complex analytical systems across data, model, pipeline, infrastructure, and application layers. Ability to balance statistical rigor, technical scalability, explainability, maintainability, and business usability when designing analytical solutions. Responsibilities: Design, develop, and maintain anomaly detection and pattern recognition systems capable of identifying unusual behaviors, emerging trends, structural changes, and complex relationships across large-scale healthcare and operational datasets. Develop statistical and machine learning models using techniques such as clustering, classification, time-series analysis, change-point detection, outlier detection, graph-based analytics, ensemble methods, and representation-learning approaches. Build analytical solutions that combine multiple data sources and signals to recognize patterns that may not be detectable through traditional rules-based or single-variable approaches. Evaluate model performance using appropriate statistical techniques and develop methods for threshold optimization, signal prioritization, false-positive reduction, model calibration, and explainability. Develop reusable feature engineering, scoring, and analytical components that can support multiple enterprise use cases rather than isolated point solutions. Apply natural language processing, large language models, and other machine learning techniques to unstructured and semi-structured information to identify patterns, themes, relationships, and emerging signals. Design and contribute to production-grade machine learning and analytical pipelines, including automated data preparation, feature generation, model training, validation, deployment, scoring, and monitoring. Develop and maintain CI/CD workflows for data science solutions, incorporating source control, automated testing, environment management, deployment automation, model versioning, release controls, and rollback capabilities. Partner with engineering and technology teams to integrate analytical models and services with enterprise applications, data platforms, APIs, workflow systems, and downstream business processes. Establish monitoring for production analytical systems, including model performance, data quality, feature drift, model drift, pipeline health, processing failures, and other operational indicators. Investigate production issues and analytical anomalies through systematic root-cause analysis, working across data, modeling, infrastructure, and application layers as needed. Contribute to architecture and technical design decisions related to scalable analytics, model serving, orchestration, integration patterns, and production machine learning. Support analytics infrastructure and tooling, including technologies such as Snowflake and Azure, to ensure solutions are scalable, reproducible, observable, secure, and aligned with enterprise technology and data governance standards. Collaborate with business, analytics, engineering, architecture, and technology stakeholders to translate complex analytical requirements into reliable technical solutions and measurable business outcomes. Research and evaluate emerging statistical, machine learning, AI, and MLOps techniques and determine their applicability to enterprise analytical problems. PamTen