Data Scientist

Role Overview

We are seeking a skilled Data Scientist to develop algorithms and data-driven models that improve manufacturing efficiency and quality control across our medical device product lines. The ideal candidate will analyze production and quality datasets to identify optimal process parameters, detect defects, and reduce variability, using machine learning, deep learning, and advanced mathematical methods. This role works closely with manufacturing, quality, and engineering teams to turn data into measurable improvements in product quality and process consistency.

Key Responsibilities

Analyze historical and real-time manufacturing data to identify optimal process parameters and procedures that improve yield, consistency, and quality across medical device production lines.

Design, build, and validate machine learning and deep learning models for defect detection, anomaly detection, predictive maintenance, and process optimization.

Develop statistical and predictive models to quantify the impact of process variables on product quality, reliability, and compliance metrics.

• Perform exploratory data analysis (EDA) to uncover patterns, correlations, and root causes of quality or yield issues.
• Build and maintain data pipelines to support continuous collection, cleaning, and preprocessing of manufacturing and sensor data.

Collaborate with manufacturing, quality assurance, and process engineering teams to translate data insights into actionable improvements and validated process changes.

Support quality control initiatives such as statistical process control (SPC), defect classification, and root-cause analysis using data-driven methods.

Communicate findings, models, and recommendations clearly to technical and non-technical stakeholders through reports, dashboards, and presentations.

Monitor deployed model performance over time and refine models as new production data becomes available.

Ensure data science work aligns with applicable quality and regulatory standards relevant to medical device manufacturing (e.g., documentation, traceability, validation practices).

• Stay current with advancements in machine learning, deep learning, and statistical methods applicable to manufacturing and quality control.
• Required Skills
• Bachelor's or Master's degree in Data Science, Statistics, Applied Mathematics, Computer Science, Engineering, or a related field.
• 2+ years of professional experience in a Data Scientist or similar analytical role.
• Strong understanding of Machine Learning and Deep Learning concepts and frameworks (e.g., scikit-learn, TensorFlow, PyTorch, Keras).
• Solid foundation in advanced mathematics and statistics (linear algebra, calculus, probability theory, optimization methods).
• Proficiency in programming languages: Python and R (required).
• Experience working with large, real-world datasets including data cleaning, feature engineering, and exploratory analysis.
• Experience with data visualization tools/libraries (e.g., Matplotlib, Seaborn, ggplot2, Plotly, or similar).

Strong analytical and problem-solving skills, with the ability to translate data insights into practical process and quality recommendations.

• Excellent communication skills, with the ability to present technical findings to cross-functional teams in English.
• Preferred Qualifications
• Experience in medical device, pharmaceutical, or other regulated manufacturing environments.
• Familiarity with quality and regulatory frameworks relevant to medical devices (e.g., ISO 13485, IEC 62304, 21 CFR Part 820/11, IQ/OQ/PQ).
• Experience with statistical process control (SPC), design of experiments (DOE), and process capability analysis.
• Familiarity with SQL and database querying for large-scale data extraction.
• Experience with time-series analysis and/or sensor/IoT data from production or test equipment.
• Experience with computer vision techniques for automated visual inspection or defect detection.
• Experience with cloud platforms (AWS, GCP, or Azure) for model deployment and data storage.
• Knowledge of MLOps practices for model versioning, monitoring, and deployment.