Data Scientist in Pennsylvania: Build Predictive Models That Save Lives

Stop analyzing static reports. Start building the predictive engines that power life-saving decisions. We’re seeking a mission-driven Data Scientist in Pennsylvania to join a forward-thinking analytics team where your code directly impacts patient outcomes and operational excellence. If you thrive on turning messy, complex datasets into clear, actionable intelligence with Python, machine learning, and cloud platforms, this is your career-defining role.

About the Role: Where Data Meets Destiny

You won't just be running queries and building dashboards. You will be a core architect of our predictive analytics pipeline, focusing on high-stakes problems in the healthcare and operational domains. Your work will involve developing and deploying scalable machine learning models that forecast patient risks, optimize resource allocation, and uncover hidden patterns in clinical and claims data. This is a hands-on, end-to-end role—from data extraction and feature engineering to model validation, deployment (using MLOps principles), and communicating findings to clinical and executive stakeholders.

You will be embedded within a collaborative team of data engineers, analysts, and domain experts, but you will own your projects with significant autonomy. We value intellectual curiosity, clean code, and the relentless pursuit of model performance and interpretability. Your primary tools will be Python (pandas, NumPy, scikit-learn, TensorFlow/PyTorch), SQL, and cloud platforms (AWS SageMaker, GCP Vertex AI, or Azure ML).

Your Impact Will Be Measurable:

• Develop & Deploy ML Models: Build, train, and productionalize classification, regression, and clustering models for predictive healthcare analytics.
• Drive Data Strategy: Partner with data engineers to improve data pipelines and ensure high-quality, accessible data for modeling.
• Translate Complexity into Clarity: Create compelling data visualizations and executive summaries that translate technical results into business and clinical actions.
• Champion Best Practices: Advocate for reproducible research, version control (Git), and rigorous model validation to ensure robustness and fairness.

What You Bring: The Ideal Profile

We are looking for a practitioner, not just a theorist. You have a proven track record of taking real-world data problems from concept to deployment. You are as comfortable discussing gradient boosting algorithms as you are explaining model limitations to a non-technical audience.

Essential Experience & Skills:

• Proven Experience: 3+ years of hands-on data science experience, with a portfolio of completed projects (please be prepared to discuss).
• Core Technical Stack: Expert proficiency in Python for data science. Advanced SQL skills. Experience with at least one major cloud ML service (AWS, GCP, Azure).
• ML Framework Mastery: Solid, practical experience with scikit-learn and at least one deep learning framework (TensorFlow/Keras or PyTorch).
• Statistical Foundation: Strong grasp of statistical inference, experimental design, A/B testing, and model evaluation metrics.
• Communication: Excellent ability to craft narratives with data. Experience creating dashboards (Tableau, Power BI, Plotly Dash) is a plus.
• Education: Bachelor’s degree in Computer Science, Statistics, Mathematics, or a related quantitative field. Master’s or PhD preferred.

Nice-to-Have Attributes:

• Direct experience with healthcare data (EHR, claims, OMOP CDM) or a regulated industry.
• Familiarity with MLOps tools for model monitoring and CI/CD (MLflow, Kubeflow, etc.).
• Knowledge of causal inference methods or time-series forecasting.

Why This Role Is Different: Your Growth & Rewards

We invest in our people because your breakthroughs are our company’s future. This isn't a siloed analytics department; you're a strategic partner from day one.

• Compensation & Security: A highly competitive salary (commensurate with experience) with a comprehensive benefits package including medical, dental, vision, and a 401(k) with company match.
• Flexibility & Balance: We offer a hybrid work model (Pennsylvania-based, with 2-3 days remote flexibility) and a generous PTO policy. We believe in output, not hours.
• Growth Trajectory: An annual professional development stipend for conferences, courses, and certifications. Regular tech talks and mentorship from senior data leaders.
• Mission & Technology: Work on problems that matter with a modern, scalable tech stack. No legacy systems—we use the right tool for the job and encourage innovation.
• Culture: A collaborative, ego-free environment that values intellectual debate, knowledge sharing, and work that has a tangible, positive impact.

Location: Pennsylvania

This role is based in Pennsylvania. We have a collaborative office space in the greater Philadelphia/Pittsburgh corridor (specific location discussed during interview). Our hybrid model is designed to foster team connection while respecting personal time. You must be authorized to work in the United States.

If you are a Data Scientist who wants your algorithms to do more than optimize clicks—if you want them to contribute to better health and smarter systems—we want to hear from you. Bring your expertise, your curiosity, and your desire to build models that matter.