Senior Data Scientist, RWD Analytics — Remote Role

Tempus AI; Boston (MA); On-site; USD 140,000 - 190,000; Full time

Benefits offered by this job

Medical benefits

Incentive compensation

Restricted stock units

Job summary

Tempus AI seeks a Senior Data Scientist focused on real-world data analytics to design, validate, and implement clinical heuristics using pipeline data. You will maintain Python-based profiling and robust data quality checks across complex healthcare datasets, including oncology-related EHR structures, to enable longitudinal cohort analyses for real-world data initiatives.

You will collaborate with clinical SMEs, ML engineers, and data scientists to define ground truth standards, validate

Qualifications

• Bachelor's or Master's degree in Computer Science, Data Science, Statistics, Mathematics, Engineering, Clinical Informatics, or a related field.
• 4+ years of experience in data science, clinical data analytics, or machine learning, with a focus on real-world healthcare data (RWD).
• Proficiency in Python and highly advanced SQL, with experience navigating complex relational databases, clinical data models, and ETL pipelines.
• Strong command of evaluation strategies and statistical analysis for AI models, NLP outputs, or clinical heuristics.
• Experience with data quality frameworks, building automated checks (e.g., via YAML configurations), and data profiling tools.
• Deep familiarity with oncology data (e.g., staging, biomarkers, radiotherapy, lines of therapy) and Electronic Health Record (EHR) data structures is highly preferred.
• Experience with data visualization tools (e.g., matplotlib, seaborn, Plotly, Tableau) to communicate data trends, evaluation metrics, and quality metrics.
• Excellent problem-solving skills, extreme attention to detail, and the ability to independently manage complex data workflows and chunking operations.
• Strong communication skills, with the ability to explain complex technical and clinical concepts to diverse stakeholders (technical and non-technical).
• Experience working in a collaborative, cross-functional team environment.

Responsibilities

• Heuristic Development: Design, implement, and formally validate heuristic rules and algorithms for derived clinical concepts using pipeline data.
• Data Profiling & Monitoring: Maintain and expand Python-based profiling pipelines.
• Data Quality Assurance: Build, refactor, and execute comprehensive data quality checks, ensuring robust schema and valueset adherence.
• Longitudinal Patient Cohorting: Design complex inclusion/exclusion funnels and execute large-scale longitudinal patient cohort pulls for strategic real-world data initiatives and specific analysis requests.
• Cross-Functional Collaboration: Collaborate with clinical SMEs, data labeling teams, ML engineers, and data scientists to define validation datasets, ground truth standards, and finalize clinical heuristic rules.
• Documentation & Reporting: Develop and maintain documentation, configuration files, and metrics for data quality, profiling results, and clinical evaluations to support transparency and continuous improvement.

Skills

Python

SQL

Data profiling

Data quality checks

NLP/AI evaluation

Communication

Team collaboration

Data visualization

Oncology data familiarity

Education

Bachelor's degree

Master's degree

Tools

Tableau

Plotly

Matplotlib

Seaborn

ETL pipelines

Job description

Tempus AI seeks a Senior Data Scientist focused on real-world data analytics to design, validate, and implement clinical heuristics using pipeline data. You will maintain Python-based profiling and robust data quality checks across complex healthcare datasets, including oncology-related EHR structures, to enable longitudinal cohort analyses for real-world data initiatives.

You will collaborate with clinical SMEs, ML engineers, and data scientists to define ground truth standards, validate