Remote Machine Learning Data Scientist

Summary

Join a dynamic team of experts in science, technology, and pharmaceuticals at Valo Health as a Staff Machine Learning Data Scientist in Epidemiology and Patient Data Products. You will lead knowledge translation machine learning models and predictions of patient data with diverse stakeholders, perform hands-on analysis and modeling of highly dimensional longitudinal patient data, contribute to the design, implementation, and evaluation of innovative machine learning approaches of patient data, be comfortable with scientific uncertainty, use your technical knowledge and intuition to articulate and break down large problems into solvable pieces, and be a dynamic and active team member.

Requirements

• MPH, MS with 5+ years or PhD in health sciences, biostatistics, or a quantitative field with 3+ years of work-related experience applying epidemiological, statistical, and/or machine learning methods to real-world datasets
• Must have 3+ years of experience developing and implementing machine learning in health care databases including electronic health records, administrative claims databases, and/or patient registries. Familiarity with medical coding ontologies and data models in US and globally (ICD, ATC, LOINC, SNOMED, CPT, HCPCS, etc.)
• Extensive experience developing and maintaining machine learning pipelines and translating machine learning output into meaningful insights for diverse audiences
• Confident in executing broad machine learning approaches, including random forest, logistic regression, dimensionality reduction, clustering, metrics, model selection, feature selection, and machine learning model explain ability
• Proficient in Python (3+ years required) and experience with machine learning, deep learning, and data science packages (e.g., scikit-learn, pytorch, statsmodels, scipy, MLlib)
• Comfortable working in ambiguous problem spaces; experience working in a start-up or agile work environment as part of cross-functional project teams
• Ability to lead and facilitate meetings and work collaboratively on multi-disciplinary project teams
• Exceptional time management, ability to prioritize multiple tasks simultaneously, and deliver products on time every time
• Enthusiastic about documentation–ensuring that all analyses are clear and reproducible with thorough documentation of key assumptions and decision points

Responsibilities

• Lead knowledge translation machine learning models and predictions of patient data with diverse stakeholders
• Perform hands-on analysis and modeling of highly dimensional longitudinal patient data, spanning electronic medical records, sequencing, and multi-omics, using R and Python in cloud environments
• Contribute to the design, implementation, and evaluation of innovative machine learning approaches of patient data to provide novel clinical insights
• Be comfortable with scientific uncertainty and embrace curiosity and creative solutions
• Use your technical knowledge and intuition to articulate and break down large problems into solvable pieces
• 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

Preferred Qualifications

• Advanced knowledge of biostatistics approaches, including inferential and predictive modeling. Experience in causal approaches for observational studies, including propensity score methods, bias adjustment, and covariate selection and adjustment is a plus
• Familiarity with or exposure to traditional drug discovery and development processes and approaches is a plus
• Familiarity with integrated clinico–omics datasets (including sequencing, genomics, proteomics, etc.) is a plus