Federated ML Data Scientist (Pharma Background) 100% Remote

Description:

Job title: Principal Data Scientist
Remote
Client s mission is to chase the miracles of science to improve people s lives. Client is a company that's on the rise. We're expanding in multiple directions, across borders and, most of all, in the way we think. At Client, we're building a team of brilliant individuals to drive the success of a new healthcare business to transform healthcare for all. People are the most critical ingredient to our success. E.D.G.E. Team (Emerging Disruptive Growth Exploration) conducts cutting-edge research in health care and incubates data-driven digital and non-digital solutions which aim to improve a person s health outcomes, the lives and ability for families to support and care for their loved ones, clinicians experience, and to reduce health care costs. We are actively incubating multiple concepts to improve the lives of individuals and their loved ones globally, especially underserved populations, and we are seeking the best and the brightest to join this journey and change healthcare for all. We are seeking an experienced and visionary Principal Data Scientist to lead our efforts in developing advanced predictive models and AI solutions for healthcare. The ideal candidate will possess a deep understanding of machine learning methodologies, a proven track record of delivering impactful data-driven solutions in a real-world setting, and the ability to drive innovation across diverse therapeutic areas.

Main Responsibilities:

The overall purpose and main responsibilities are listed below:
o Lead the design, development, and deployment of cutting-edge predictive models using various machine learning and AI techniques, including tree-based models (e.g., XGBoost) and transformer-based architectures (e.g., BERT), for early disease detection and proactive interventions.
o Drive the strategic direction of data science initiatives across multiple therapy areas, identifying opportunities to leverage real-world data (e.g., open claims data, EHR) for improved patient outcomes and drug development, including the use of federated analytics and federatML.
o Provide technical leadership and mentorship to a team of data scientists, fostering a culture of innovation, rigorous experimentation, and best practices in MLOps.
o Evaluate and select appropriate modeling techniques and performance metrics (e.g., Precision, Recall, Bayes factor, NNT) based on specific problem statements and business objectives.
o Collaborate closely with cross-functional teams including business owners, payers, clinicians, epidemiologists, statisticians, and IT to translate complex business problems into tractable data science solutions for deployment in real world.
o Stay abreast of the latest advancements in machine learning, deep learning, and AI, and proactively integrate novel approaches into our predictive modeling capabilities.
o Communicate complex analytical findings and their implications clearly and concisely to both technical and non-technical audiences.

About you:

• PhD or Master's degree in a quantitative field (e.g., Computer Science, Statistics, Biomedical Informatics, Engineering, Physics).
  8+ years of progressive experience in data science, with a significant portion focused on predictive modeling and advanced analytics in healthcare or life sciences.
  Demonstrated expertise in machine learning algorithms and deep learning architectures, including strong practical experience with transformer models (e.g., BERT).
  Proficiency in programming languages such as Python or R, and experience with relevant data science libraries (e.g., scikit-learn, TensorFlow, PyTorch, XGBoost).
  Experience working with large-scale, real-world healthcare datasets such as claims data, electronic health records (EHR), or clinical trial data.
  Strong understanding of statistical concepts and experimental design.
  Proven ability to lead complex data science projects from conception to deployment, with a focus on delivering measurable business impact.
  Excellent communication, interpersonal, and leadership skills, with the ability to influence and collaborate effectively across all levels of the organization.

Comments:
Possibility of extension

Open to all time zones in US however must be able to work EST hours

Must Have :

• Min of 8 years of related experience
• Previous Pharma experience required
• ML experience required
• Federated analytics and federatML must have
• Deep Learning transformer architecture, transformer-based architecture is required
• Application in healthcare is essential, EMR, claims data, genomic data exp required
• Python, R
• Experience in healthcare/ biostats/Case control studies etc.

Nice to Have :

• C++ (highly desirable)