Senior Biostatistics and Data Science Associate - Machine Learning Engineer

Summary

Develop, test, and maintain data-driven analytic pipelines for the analysis and reporting of biomedical data. Working with a team of physician scientists and informaticians at Baylor College of Medicine, the data science associate will utilize big data extracted from electronic health records (EHRs) from multiple large academic cancer centers with the goals to advance Learning Health Systems. The specific tasks involve phenotyping of diseases (involves understanding of ICD-10-CM, CPT, UMLS vocabularies, natural language processing pipelines, and finetuning/application of existing biomedical large language models), deriving/validating prediction models for specific outcomes (involves knowledge of statistical associations, deep learning, neural networks, transformers, transferred learning), and translating models into actionable knowledge to impact patient care (involves knowledge of software development, API implementation/integration with native EHR such as Epic). Prior knowledge in Python (Pandas, NumPy, Seaborn, Scikit-learn, TensorFlow vs PyTorch) and SQL are required.

Job Duties

• Curious and excited to work in cutting-edge big data healthcare research using advanced AI/ML methodologies to design, code, test, and maintain novel software system with moderate complexity to integrate external data and software tools for multi-platform and multi-center informatics applications.
• Eager and willing to collaborate with team members from diverse backgrounds (clinical, epidemiological, and data science) regarding requirements, schedules, and activities; troubleshoot development and production problems across multiple environments and platforms.
• Adapt and test proprietary and open-source data analysis pipelines on various computing platforms for the analysis and reporting of biomedical data, with emphases on data-driven algorithms for data cleaning, classification, regression, anomaly detection, and prediction.
• Deploy the pipelines, monitor their executions, interpret results, customize pipelines to improve the performance of data-driven pipelines.
• Prepare documented observations, analyses and interpretations of results including technical reports, summaries, protocols and quantitative analyses.
• Support users by maintaining documentation and producing and analyzing reports; maintain communications with software engineering and programming stakeholders.
• Present and publish results in peer-reviewed journals and relevant scientific conferences.
• Performs other job related duties as assigned.

Minimum Qualifications

• Bachelor's degree.  
• Four years of relevant experience.

Preferred Qualifications

• Master’s degree in bioinformatics, biostatistics, medical informatics, or related disciplines
• Four years of relevant experience. Two years of relevant experience for candidates with Ph.D. degrees or multiple master’s degrees.
• Proficient in at least one of Python and R programming languages, with demonstrated skills in data manipulation and software engineering.
• Having prior experience in healthcare data analysis.
   

 

 

Baylor College of Medicine is an Equal Opportunity/Affirmative Action/Equal Access Employer.

 

 

 17891