Welcome Back

Google icon Sign in with Google
OR
I agree to abide by Pharmadaily Terms of Service and its Privacy Policy

Create Account

Google icon Sign up with Google
OR
By signing up, you agree to our Terms of Service and Privacy Policy
Instagram
youtube
Facebook

Senior Manager, Data Science

Bristol Myers Squibb
5+ years
Not Disclosed
Hyderabad
1 June 3, 2026
Job Description
Job Type: Full Time Education: M.Pharm/B.Pharm or M.Sc. Skills: Medical Coding, Medical Terminology, mRS and EQ-5D-5L., Narrative Writing, Research & Development, Technical Skill, Triage of ICSRs, WHO DD Coding

Senior Manager, Data Science

Location: Hyderabad, Telangana, India
Department: Digital Health Data Science
Level: Senior Manager
Travel Requirement: Less than 10%
Company: Bristol Myers Squibb (BMS)

Position Summary

Bristol Myers Squibb Digital Health is seeking a highly skilled and hands-on Senior Manager, Data Science to develop advanced analytics solutions and machine learning algorithms using wearable and sensor-derived longitudinal health data.

This role is focused on end-to-end data science execution, from raw signal processing and quality control through feature engineering, statistical analysis, machine learning, and deployment-ready model development. The successful candidate will work extensively with accelerometry, actigraphy, heart rate variability (HRV), SpO₂, and other physiological sensor data to generate clinically meaningful insights.

This is a highly technical individual contributor role requiring significant hands-on coding, model development, code review, and analytical problem-solving.


Key Responsibilities

Wearable Data Analytics and Signal Processing

  • Design, develop, and maintain scalable Python pipelines for wearable and sensor-generated time-series data.

  • Perform:

    • Data quality control (QC)

    • Signal preprocessing

    • Sensor artifact detection and removal

    • Missing data handling and imputation

    • Feature extraction and engineering

    • Signal characterization and exploratory analysis

  • Analyze data generated from:

    • Accelerometry

    • Actigraphy

    • Heart Rate Variability (HRV)

    • Oxygen Saturation (SpO₂)

    • Other digital health sensors

Machine Learning and Model Development

  • Develop and validate advanced analytical models for longitudinal physiological data.

  • Apply:

    • Statistical learning methods

    • Deep learning architectures

    • Representation learning techniques

    • Ensemble learning approaches

    • Transformer-based models

  • Implement explainable AI methodologies where appropriate.

  • Develop models that identify clinically meaningful measures associated with disease progression, patient stratification, and disease subtyping.

Signal Processing and Digital Biomarker Development

  • Apply advanced signal processing techniques including:

    • Digital filtering

    • Frequency domain analysis

    • Time-frequency analysis

    • Signal detection algorithms

  • Support development of digital biomarkers and physiological indicators from wearable sensor data.

Statistical Modeling

  • Develop and implement longitudinal statistical models including:

    • Mixed-effects models

    • Hierarchical models

    • Repeated-measures analyses

  • Address challenges associated with:

    • Within-subject variability

    • Missing data

    • Longitudinal study designs

Validation and Reproducible Research

  • Implement rigorous model validation methodologies including:

    • Nested Cross-Validation

    • Leave-One-Out Validation (LOO)

    • Out-of-Bag (OOB) Evaluation

  • Maintain reproducible analytical workflows and well-documented codebases.

  • Ensure compliance with scientific and engineering best practices.

Collaboration and Stakeholder Engagement

  • Partner with:

    • Clinical Scientists

    • Biostatisticians

    • Software Engineers

    • Product Teams

    • External Research Partners

  • Validate third-party analytics outputs and vendor-delivered models.

  • Translate complex technical findings into actionable insights for both technical and non-technical audiences.

Technical Leadership

  • Conduct code reviews and maintain engineering quality standards.

  • Mentor team members on technical best practices when required.

  • Promote scalable, maintainable, and production-ready analytical solutions.


Required Qualifications

Education

Preferred:

  • PhD in:

    • Data Science

    • Biostatistics

    • Biomedical Engineering

    • Computer Science

    • Applied Mathematics

    • Related Quantitative Discipline

Acceptable:

  • Master's Degree with significant relevant industry experience.


Required Experience

  • Extensive experience working with wearable and sensor-generated time-series data.

  • Proven expertise in:

    • Data quality control

    • Signal preprocessing

    • Artifact handling

    • Imputation methodologies

    • Feature engineering

    • Longitudinal data analysis

  • Experience working with:

    • Accelerometry

    • Actigraphy

    • HRV

    • SpO₂

  • Strong background in machine learning and statistical modeling.