Data Science Team Lead

Mass General Brigham; Boston (MA); Remote; USD 120,000 - 160,000; Full time

Job summary

Mass General Brigham is seeking a Data Science Team Lead to oversee data science activities in multi-year studies focused on health. The role involves leading a team, performing machine learning analyses, and mentoring staff while contributing to scientific publications. The ideal candidate will have a PhD, extensive statistical and programming skills, and at least 7 years of experience.

Qualifications

• Advanced formal training in computer science.
• Minimum of 7 years related experience.
• Experience with statistical adjustment procedures for confounding and bias.

Responsibilities

• Lead data science strategy and execution across all projects.
• Assemble and analyze datasets of observational data and clinical outcomes.
• Mentor and train data science staff members.

Skills

Statistical analysis

Machine learning

Data visualization

Programming in R

Programming in Python

Analytical skills

Education

PhD in biostatistics, statistics, applied mathematics, data science, or related field

Job description

Site: The Brigham and Women's Hospital, Inc.

Mass General Brigham relies on a wide range of professionals, including doctors, nurses, business people, tech experts, researchers, and systems analysts to advance our mission. As a not-for-profit, we support patient care, research, teaching, and community service, striving to provide exceptional care. We believe that high-performing teams drive groundbreaking medical discoveries and invite all applicants to join us and experience what it means to be part of Mass General Brigham.

Job Summary

Data Science Team Lead to direct all data science activities on several multi-year industry-sponsored studies focused on health and wellness. This individual will lead a team of data scientists in performing advanced statistical and machine learning analysis of longitudinal and cross-sectional data with a focus on making robust inferences related to health and wellness.

Qualifications

The MacRae Lab is seeking a dynamic and experiences Data Science Team Lead to direct all data science activities on several multi-year industry-sponsored studies focused on health and wellness. This individual will lead a team of data scientists in performing advanced statistical and machine learning analysis of longitudinal and cross-sectional data with a focus on making robust inferences related to health and wellness. Qualified candidates will have advanced formal training in computer science, including design and analysis of observational and experimental studies, causal inference, and strong statistical computing and programming skills. Comfort with a broad range of data types, including sensor and survey data is required. The candidate will work with senior & junior data scientists and report directly to senior leadership. The candidate will also work directly with the sponsor’s data science teams. The team lead will be the sounding board for the entire data science operation, guiding, training, and mentoring the other staff members. There will be the opportunity for career development with respect to authorship opportunities for journal manuscripts and abstracts/posters for professional scientific meetings.

This role will be responsible for working with large scale raw sensor data. The analytical strategy will be based primarily on longitudinal analyses and machine learning techniques. Longitudinal analyses will employ mixed-effects models to understand parameter distributions over time. Machine learning algorithms like Random Forests will be used to predict clinical outcomes, emphasizing interpretable models and features of importance. Raw sensor data (and derived physiological metrics) will be processed and transformed into meaningful/analyzable features, including removal of noisy measurements and imputation of missing values when applicable. Preprocessing will be applied to each sensor and physiological measure, focusing on capturing characteristics that are most important for resilience marker identification. This position is expected to be the lead data scientist on the projects and will be responsible for independently determining appropriate pathways and setting the standard for junior staff.

PRINCIPAL DUTIES AND RESPONSIBILITIES:

Lead data science strategy and execution across all projects, ensuring scientific rigor and reproducibility.

Assemble and explore multiple large datasets of observational data, both survey and sensor based, to define and test hypotheses related to predictors of health, disease and resilience (~25%)

Assemble and explore datasets of clinical outcome data from electronic health records (e.g., hospital readmissions, adverse events, lab values) that are potentially associated with readouts from wearable sensor data (~25%)

Lead and perform statistical analyses (including planning, programming, analysis, interpretation, visualization and writing of results) to address research questions (~25%)

Prepare and write all components of manuscripts, abstracts, and presentations at scientific meetings with assistance from Chief Data Scientist and Principal Investigator

Building machine learning predictive models using a variety of inputs derived from wearable device sensors

Mentor, guide, and train all data science staff members. This will included organizing growth opportunities such as journal clubs, poster presentations, etc…

Work with senior leadership to determine staffing needs and participate directly in the hiring and firing of data science staff.

Present work internally and to study sponsor in both scientific and non-scientific settings

Provide feedback regarding newly proposed study instruments and questionnaires

Write code using a collaborative version control system, ensuring proper documentation and periodic refactoring

Rearrange data in a format that allows for accurate use as well as possible integration and pooling across multiple data sets

Ability to incorporate clinical inferences in data analysis, specifically elements of HR, HRR, HRV, VO2 Max

Maintain department service standards as outlined in the BWH Code of Conduct

Performs other duties as required and as appropriate

QUALIFICATIONS:

• PhD in biostatistics, statistics, applied mathematics, data science, computer science, or related field required
• Experience dealing with statistical adjustment procedures for confounding, selection bias, data missingness, and measurement error
• Formal training in experimental design
• Minimum of 7 years of related experience
• Expertise in statistical computing; expertise in R and Python required

SKILLS/ ABILITIES/ COMPETENCIES REQUIRED:

• Ability to formulate hypotheses, draw conclusions and deliver results
• Experience with biomedical data or wearable data preferred
• Proficiency in data visualization
• Advanced skillset coding in R and Python
• Experience with longitudinal and cross-sectional analysis
• Possess strong analytical skills

• Ability to prioritize assignments, multi-task, make decisions based upon sound principles, and independently problem solve
• Ability to develop novel ways to coordinate, manage and report data
• Demonstrated sound independent judgment and competencies in clinical research
• Excellent verbal and written communication skills
• Detail and process oriented
• Ability to work independently as well as part of a team

Additional Job Details (if applicable)

Remote Type

Remote

Work Location

221 Longwood Avenue

Scheduled Weekly Hours

40

Employee Type

Regular

Work Shift

Day (United States of America)

EEO Statement:

The Brigham and Women's Hospital, Inc. is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religious creed, national origin, sex, age, gender identity, disability, sexual orientation, military service, genetic information, and/or other status protected under law. We will ensure that all individuals with a disability are provided a reasonable accommodation to participate in the job application or interview process, to perform essential job functions, and to receive other benefits and privileges of employment. To ensure reasonable accommodation for individuals protected by Section 503 of the Rehabilitation Act of 1973, the Vietnam Veteran’s Readjustment Act of 1974, and Title I of the Americans with Disabilities Act of 1990, applicants who require accommodation in the job application process may contact Human Resources at (857)-282-7642. Mass General Brigham Competency Framework

At Mass General Brigham, our competency framework defines what effective leadership “looks like” by specifying which behaviors are most critical for successful performance at each job level. The framework is comprised of ten competencies (half People-Focused, half Performance-Focused) and are defined by observable and measurable skills and behaviors that contribute to workplace effectiveness and career success. These competencies are used to evaluate performance, make hiring decisions, identify development needs, mobilize employees across our system, and establish a strong talent pipeline.