Assoc Principal Scientist (Assoc. Director) Real World Evidence Capability Analytics

MSD•Rahway, PA

8h•Hybrid

About The Position

Job Description: We are seeking a highly skilled and motivated Associate Principal Scientist/Associate Director with expertise in conducting outcome researching using real world data. This role requires the ability to analyze complex data sets, develop algorithms, and create innovative solutions to enhance our data-driven decision-making processes. Key Responsibilities: Real World Data Analysis: Analyze and interpret large volumes of structured and unstructured real-world patient level healthcare data, including but not limited to administrative claims, EHR/EMR, disease registry, and public-use databases. Develop machine learning algorithms and statistical/survival analysis models to extract meaningful insights and outcome research evidence. Collaboration And Communication : Work closely with stakeholders in outcome research, medical affairs, statistical programming, and IT functions to provide data-driven insights and solutions. Provide data science and real-world data expert inputs in internal and external collaborations. Present research findings in internal and external scientific congress meetings. Project Management: Independently lead Real-World Evidence outcome research or advanced AI/machine learning research projects with minimum supervision. Continuous Learning and Innovation : Stay current with the latest research and technologies in data science and machine learning. Proactively seek opportunities to improve existing processes and methodologies. Qualifications: Required Skills & Qualifications: Proficiency in Machine Learning and Statistical Programming using tools such as R, SAS, or Python, with a strong foundation in model development and data analysis. Advanced SQL skills for efficient data querying, manipulation, and transaction management across complex datasets. Extensive hands-on experience with Real-World Data (RWD) sources including administrative claims, EHR/EMR systems, patient registries, and public-use databases, with a proven track record of generating Real-World Evidence (RWE). Expertise in cohort identification using clinical and therapeutic classification codes such as ICD-9-CM, ICD-10-CM, SNOMED, LOINC, NDC, HCPCS, and CPT. Experience in developing study protocols for non-interventional and methodological research studies, including observational and retrospective designs. Working knowledge of research project operations, including contracting, procurement, and budget management processes. Strong interpersonal and communication skills, with a keen attention to detail, clarity, and precision in documentation and collaboration. Ability to manage multiple analytical projects simultaneously, often across diverse therapeutic areas, with effective planning and organizational skills. Required Education & Professional Experience: Master’s degree in a relevant field (e.g., Epidemiology, Biostatistics, Public Health, Data Science) with a minimum of 5 years of post-graduate experience conducting research using real-world healthcare data. Doctoral degree (PhD, ScD, DrPH) in a related discipline with at least 2 years of post-graduate experience in real-world healthcare data research. Preferred Experience & Skills: Strong foundational knowledge of statistical and machine learning concepts, with practical application in real-world healthcare data contexts. Proven experience leading Real-World Evidence (RWE) studies within biomedical research or healthcare organizations. Experience of implementing outcome research studies in following disease and therapeutical areas - heart failure, PAH, COPD, IBD, Ophthalmology Hands-on experience applying large language models (LLMs) such as BioBERT, MedBERT, or similar, to clinical data for research purposes. Demonstrated ability to mentor and support junior team members, fostering growth and collaboration within research teams. Co-authorship of peer-reviewed publications involving data science methodologies, and/or active participation in data-focused competitions such as datathons, hackathons, or Kaggle challenges—ideally centered on real-world healthcare data. (Please include bibliographic references, competition leaderboard URLs, and GitHub repositories in your Resume/CV.)

Requirements

Proficiency in Machine Learning and Statistical Programming using tools such as R, SAS, or Python, with a strong foundation in model development and data analysis.
Advanced SQL skills for efficient data querying, manipulation, and transaction management across complex datasets.
Extensive hands-on experience with Real-World Data (RWD) sources including administrative claims, EHR/EMR systems, patient registries, and public-use databases, with a proven track record of generating Real-World Evidence (RWE).
Expertise in cohort identification using clinical and therapeutic classification codes such as ICD-9-CM, ICD-10-CM, SNOMED, LOINC, NDC, HCPCS, and CPT.
Experience in developing study protocols for non-interventional and methodological research studies, including observational and retrospective designs.
Working knowledge of research project operations, including contracting, procurement, and budget management processes.
Strong interpersonal and communication skills, with a keen attention to detail, clarity, and precision in documentation and collaboration.
Ability to manage multiple analytical projects simultaneously, often across diverse therapeutic areas, with effective planning and organizational skills.
Master’s degree in a relevant field (e.g., Epidemiology, Biostatistics, Public Health, Data Science) with a minimum of 5 years of post-graduate experience conducting research using real-world healthcare data.
Doctoral degree (PhD, ScD, DrPH) in a related discipline with at least 2 years of post-graduate experience in real-world healthcare data research.

Nice To Haves

Strong foundational knowledge of statistical and machine learning concepts, with practical application in real-world healthcare data contexts.
Proven experience leading Real-World Evidence (RWE) studies within biomedical research or healthcare organizations.
Experience of implementing outcome research studies in following disease and therapeutical areas - heart failure, PAH, COPD, IBD, Ophthalmology
Hands-on experience applying large language models (LLMs) such as BioBERT, MedBERT, or similar, to clinical data for research purposes.
Demonstrated ability to mentor and support junior team members, fostering growth and collaboration within research teams.
Co-authorship of peer-reviewed publications involving data science methodologies, and/or active participation in data-focused competitions such as datathons, hackathons, or Kaggle challenges—ideally centered on real-world healthcare data. (Please include bibliographic references, competition leaderboard URLs, and GitHub repositories in your Resume/CV.)

Responsibilities

Analyze and interpret large volumes of structured and unstructured real-world patient level healthcare data, including but not limited to administrative claims, EHR/EMR, disease registry, and public-use databases.
Develop machine learning algorithms and statistical/survival analysis models to extract meaningful insights and outcome research evidence.
Work closely with stakeholders in outcome research, medical affairs, statistical programming, and IT functions to provide data-driven insights and solutions.
Provide data science and real-world data expert inputs in internal and external collaborations.
Present research findings in internal and external scientific congress meetings.
Independently lead Real-World Evidence outcome research or advanced AI/machine learning research projects with minimum supervision.
Stay current with the latest research and technologies in data science and machine learning.
Proactively seek opportunities to improve existing processes and methodologies.