Lead Data Scientist – Patient Analytics, Machine Learning & MLOps

About PharmSight

PharmSight is a rapidly growing strategic consulting firm dedicated to advancing bio-pharmaceutical innovation. We deliver bespoke solutions that address critical business challenges across the pharmaceutical value chain, including competitive intelligence, forecasting, commercial analytics, and advanced data science.

As we continue to expand our advanced analytics capabilities, we are seeking a Lead Data Scientist to join our team and drive the development of machine learning solutions using real-world healthcare data.

Why Join PharmSight?

• High-Impact Work: Build advanced analytics and machine learning solutions using real-world pharma datasets
• Work Flexibility: Freedom to work anytime and from anywhere
• Client Exposure: Work closely with global pharma clients on cutting-edge analytics initiatives
• Career Growth: A flat hierarchy with strong opportunities for ownership, innovation, and leadership

Role Overview

We are seeking a highly experienced Lead Data Scientist to drive advanced predictive modeling and machine learning initiatives across patient analytics and broader AI-driven business use cases. This role requires a hands-on expert who can independently translate business problems into analytical approaches, build and validate robust machine learning models, engineer features from complex longitudinal datasets, and deliver scalable, production-ready solutions with minimal supervision. The individual will work across the full lifecycle of applied analytics, from exploratory analysis and hypothesis generation to model development, deployment, and ongoing optimization. In addition to solving high-impact patient analytics problems, this role will also contribute to the design and build of internal AI/ML products, accelerators, and intelligent analytics capabilities that support future innovation across the organization.

ROLES & RESPONSIBILITIES

• Lead end-to-end development of machine learning solutions for patient analytics and related commercial or clinical use cases.
• Independently explore data, frame problems, generate hypotheses, engineer features, train models, validate outcomes, and communicate insights clearly to technical and non-technical stakeholders.
• Build and optimize classification models using methods such as Random Forest, XGBoost, Logistic Regression, and other suitable algorithms based on the business context.
• Design robust modeling pipelines for longitudinal patient-level data, including feature engineering from journeys, events, sequences, and time-based interactions.
• Apply strong model validation techniques including train-test split, cross-validation, out-of-bag validation, and performance evaluation for imbalanced classification problems.
• Develop scalable and reproducible ML workflows, including experiment tracking, model versioning, deployment, and monitoring using MLOps best practices.
• Work with global cross-functional stakeholders to understand business questions, challenge assumptions, propose better analytical approaches, and deliver decision-ready outputs.
• Act as a subject matter expert in solving development and commercial questions using predictive, prescriptive, and applied analytics.
• Perform exploratory and targeted data analyses using statistical techniques, descriptive methods, and hypothesis-driven problem solving.
• Contribute to the design and build of internal AI/ML-based products, accelerators, intelligent dashboards, and automation solutions.
• Partner with engineering and product teams to translate business needs into technical specifications and deploy production-grade analytics assets.
• Work in Linux-based development environments and manage code, environments, and collaboration workflows using Git and related tools.
• Contribute to roadmap discussions for AI tools, reusable data science assets, and future-facing patient analytics capabilities.
• Where relevant, support feature extraction from unstructured text such as medical notes, EMR, or other healthcare text sources using NLP, clinical NLP, NER, or LLM-based approaches.

FUNCTIONAL SKILLS

Must-Have Skills

• 5–7 years of hands-on industry experience in data science, machine learning, or advanced analytics, with the ability to contribute independently from day one.
• Strong proficiency in Python for data science, including Pandas, NumPy, data manipulation, efficient/vectorized processing, and model development using Scikit-learn.
• Strong experience in building and evaluating classification models, with expertise in methods such as Random Forest, XGBoost, and Logistic Regression.
• Solid understanding of model validation and performance assessment, including train-test split, cross-validation, out-of-bag validation, and evaluation of imbalanced classification problems using metrics such as precision, recall, F1, and AUC.
• Strong experience in feature engineering for longitudinal or patient-level journey data, including temporal, event-based, and derived behavioral features.
• Strong familiarity with Linux-based development environments, command-line workflows, remote development practices, and Git-based version control.
• Excellent written and verbal communication skills, with the ability to clearly communicate analytical approaches, findings, limitations, and recommendations to both technical and non-technical stakeholders.
• Strong problem-solving and critical-thinking skills, including the ability to challenge assumptions, assess proposed approaches, and develop alternative solutions independently.

Strongly Preferred Skills

• Experience working with US pharmaceutical claims, real-world data, or other patient-level healthcare datasets for machine learning and predictive modeling.
• Familiarity with common healthcare and patient analytics data sources such as medical claims, pharmacy claims, prescription data, EMR/EHR, lab data, specialty pharmacy data, and patient support program / copay datasets.
• Foundational understanding of the US pharmaceutical ecosystem, including patient access, real-world evidence, treatment pathways, adherence, persistence, and patient support services.
• Experience in cohort design, response generation, label creation, and handling common data quality and interpretation caveats associated with healthcare claims and longitudinal patient data.
• Working knowledge of cloud-based data environments, particularly AWS, including S3, Athena, and related Python-based workflows.

Good-to-Have Skills

• Experience with MLOps frameworks and tools such as MLflow, Kubeflow, Airflow, SageMaker, or comparable platforms.
• Experience with model deployment, productionization, and monitoring, including exposure to Docker, Kubernetes, and CI/CD workflows.
• Familiarity with Databricks for data science, analytics engineering, and MLOps workflows.
• Proficiency with additional machine learning libraries and frameworks such as TensorFlow or PyTorch, where relevant.
• Experience with NLP and text analytics, including feature extraction from unstructured healthcare text, clinical notes, EMR text, clinical NER, or LLM-based approaches.
• Experience in time-series analysis, forecasting, or trend-based modeling.
• Experience with data engineering and pipeline development, including ingestion, transformation, orchestration, and scalable data processing.
• Exposure to cloud platforms such as AWS, Azure, or GCP for analytics and machine learning workloads.

Soft Skills

• High degree of ownership, initiative, and accountability.
• Ability to work effectively in cross-functional, and collaborative environments.
• Strong analytical mindset with a structured approach to problem solving.
• Ability to balance technical depth with business relevance.
• Strong stakeholder management and interpersonal skills.
• Curiosity, adaptability, and willingness to work across evolving AI/ML use cases.

PROFESSIONAL CERTIFICATIONS

(Preferred, not mandatory)

• AWS Machine Learning / Developer / Data Analytics certification
• Databricks Data Scientist or Machine Learning certification
• Relevant Python, Machine Learning, MLOps, or Cloud certifications

BASIC QUALIFICATIONS

• Master’s degree in Data Science, Statistics, Computer Science, Mathematics, Engineering, Bioinformatics, or another quantitative STEM discipline with 5+ years of relevant industry experience;

OR

• Bachelor’s degree in a quantitative or technical field with 7+ years of relevant industry experience.

Join Us

Join PharmSight and contribute to building advanced analytics and machine learning solutions that transform real-world healthcare data into actionable insights. If you are passionate about solving complex problems using data science and enjoy working with large healthcare datasets, we would love to hear from you.

Interested? Apply now, and we will get back to you soon.