Data Scientist, RWD

As a Data Scientist of Real World Data, you will be a core member of a team of data scientists and data engineers building a powerful computational platform for advancing the discovery and development of new medicines. In this role, you will help curate and leverage real-world data (e.g. electronic medical record databases) to support drug development research hypothesis studies and machine learning pipelines. To do so, you will work under the guidance of colleagues in clinical informatics, epidemiology, data engineering, and machine learning to develop solutions to challenging computational problems. Successful candidates will be at the forefront of developing patient data tools and their uptake across Valo’s diverse scientific teams in an innovative startup environment that is pushing the boundaries of drug discovery.

• Work in close partnership with a cross-functional data science team to optimize patient data utilization, and ensure high quality datasets for research and development
• Support data harmonization standards, curation strategy, and mappings of clinical concepts from available electronic medical record and biobank registry databases. This requires developing in-depth knowledge of Valo’s patient data sources and how they’re used by partner teams in drug discovery research.
• Break down business and research requirements into actionable steps in an agile and responsive manner. Lead the subsequent execution of data analysis or feasibility studies and contribute to preparing deliverables for internal and external stakeholders.
• Support the development and maintenance of user-driven tools to generalize data processes and automate data transformation in real-world data studies and machine learning projects. Seek out opportunities to improve these tools from user feedback.
• Autonomously perform high-quality and reproducible analysis within a cloud environment using R or Python
• Be a dynamic and active team member, championing and adopting shared coding standards, participating in code review, and providing regular updates of your work and input into the work of your colleagues

• Bachelor’s with 3+ years of patient data experience or MS with 1 + year with a quantitative focus (public health, health economics, biostatistics) or in in a quantitative field (computer science, statistics, computational biology, biomedical engineering). Bachelor’s with 5+ years of experience or MS / PhD with 3+ years for Senior DS role.
• 1+ year of experience querying and curating structured and unstructured electronic health record data. 3+ years for Senior DS role.
• Demonstrated ability to execute robust analytical strategies using health care databases including electronic health records, administrative claims databases, and/or patient registries
• Must have experience conducting data manipulation, analysis, and visualization in Python and/or R programming languages
• Exceptional time management, ability to prioritize multiple tasks simultaneously, and deliver products on time

• Knowledge of medical coding ontologies and data models for real-world data types in US and globally (ICD, ATC, LOINC, SNOMED, CPT, HCPCS, etc)
• Familiarity and/or experience with Spark (pyspark) including performance optimization through query techniques, data storage techniques, or configuration tuning
• Familiarity and/or experience with cloud computing (AWS), Linux environments, and shell scripting
• Familiarity with cloud analytics platforms (e.g. Snowflake) for developing ETL pipelines or dashboard visualizations (e.g Streamlit)
• Experience implementing machine learning models using real world clinical data and/or translating output into meaningful insights for diverse audiences is a plus
• Familiarity and/or experience in common clinical practices, human physiology, or epidemiology of cardiovascular, metabolic, and renal disease areas is a plus
• Familiarity with or exposure to traditional drug discovery and development processes and approaches is a plus