Data Science Intern at Jobright.ai Framingham, MA

Jobright.ai; Framingham (MA); On-site; USD 34,440 - 48,216; Full time

Job summary

Jobright.ai is seeking a Data Science Intern in Framingham, MA, to contribute to research projects focused on enhancing digital bioprocessing systems through advanced machine learning and data engineering techniques. The successful candidate will work full-time, applying skills in Python and machine learning while supporting the development of predictive models and data integration pipelines.

The ideal applicant is currently pursuing a master's degree or PhD and will gain valuable experience in a collaborative environment, contributing to innovations in biopharmaceutical processes.

Qualifications

• Currently enrolled in a master's degree or PhD program with expectations to complete by Spring 2028.
• Must be able to work 40hrs/week, Monday-Friday.
• Experience with machine learning libraries.

Responsibilities

• Develop and validate predictive models for bioprocess control.
• Apply machine learning techniques to bioprocess datasets.
• Collaborate with teams to integrate models into monitoring systems.

Skills

Python

Data analysis

Machine learning

Deep learning

Statistical analysis

Education

Master's or PhD in Data Science, Computer Science, Bioinformatics, Chemical Engineering, or related field

Tools

scikit-learn

TensorFlow

PyTorch

SQL

Job description

Data Science Intern job at Jobright.ai. Framingham, MA.

Verified Job On Employer Career Site

Overview

Sanofi is an innovative global healthcare company dedicated to improving people’s lives. They are seeking a highly motivated Data Science Co-op to contribute to a research project focused on developing and deploying advanced machine learning and data engineering techniques to enhance digital bioprocessing systems.

Responsibilities

• Machine Learning (ML): Predictive models that help monitor and forecast critical process parameters (CPPs) and quality attributes (CQAs), driving continuous improvement in biomanufacturing. These models allow for early detection of potential process deviations and ensure that desired product qualities are maintained.
• Deep Learning (DL): DL algorithms, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), can capture non-linear relationships in complex bioprocess data, such as time-series or spectral information, that cannot be identified with traditional methods. These insights lead to more accurate predictions and optimization of processes.
• Image Processing & Computer Vision: This technology is used for the analysis of visual data from bioreactors, cell cultures, and other bio-manufacturing instruments. It can assist with detecting anomalies, identifying patterns in cell growth, and ensuring the stability of cultures, all of which help in process optimization.
• Digital Twins & Soft Sensors: These tools simulate physical bioprocesses in real-time and predict their behavior using sensor data. By employing digital twins, you can test, monitor, and optimize bioprocesses virtually, improving decision-making capabilities and process design.
• Process Analytical Technology (PAT): Data science is a critical enabler of PAT, which is an industry framework aimed at ensuring quality throughout the manufacturing process. By leveraging advanced analytics and real-time monitoring, PAT can be used to develop proactive strategies that detect and control process variations, leading to improved process consistency and product quality.
• Develop, train, and validate predictive models to support decision-making processes for bioprocess control.
• Apply machine learning and deep learning techniques to large-scale bioprocess datasets, including time-series data and sensor outputs.
• Use multivariate data analysis (MVDA) techniques to analyze complex, high-dimensional datasets and extract key process insights.
• Clean, preprocess, and structure data from various sources (e.g., sensors, spectrometers, batch records).
• Assist in designing and implementing data pipelines for real-time data collection, storage, processing, and visualization on digital bioprocessing platforms.
• Collaborate with teams to integrate predictive models into bioprocess monitoring systems.
• Contribute to the development of digital twins and soft sensor frameworks that simulate bioprocess performance and provide real-time decision support.
• Develop models to predict process deviations, improve efficiency, and ensure high-quality outcomes in biologics production.
• Support automation efforts by integrating machine learning models into decision-making workflows that optimize process control and reduce variability.
• Analyze complex datasets to generate actionable insights into bioprocess performance and suggest improvements.
• Work with biologists, process engineers, and other stakeholders to interpret model outputs and translate them into experimental or process optimization recommendations.
• Develop and deploy predictive or classification models for monitoring critical process parameters (CPPs) and quality attributes (CQAs).
• Create prototypes of data integration pipelines that enable the seamless flow of real-time data into digital dashboards or simulation models.
• Contribute to scientific reports, presentations, and publications that document methodology, results, and insights gained through model development.
• Provide recommendations for data science strategies and tools that enhance biomanufacturing process control and enable smarter, faster decision-making.

Qualifications

Required:

• Currently enrolled and pursuing a master’s degree or PhD in Data Science, Computer Science, Bioinformatics, Chemical Engineering, Biostatistics, or related quantitative discipline at an accredited college or university with the expectation that you will complete your current degree by the Spring of 2028.
• Must be able to relocate to the office location and work 40hrs/week, Monday-Friday, for the full duration of the co-op/internship.
• Experience with Python or R for data analysis and machine learning modeling.
• Experience with machine learning libraries (e.g., scikit-learn, XGBoost, TensorFlow, PyTorch).
• Must be permanently authorized to work in the U.S. and not require sponsorship of an employment visa (e.g., H-1B or green card) at the time of application or in the future.

Preferred:

• Experience with Process Analytical Technology (PAT), digital twins, soft sensors, or other data-driven tools in bioprocessing.
• Exposure to omics data, process data integration, or other biotech-related datasets.
• Coursework or research experience in bioprocessing, process control, or biosystems engineering.
• Understanding of statistical analysis, data visualization, and basic ML model evaluation techniques.
• Familiarity with time-series data, dimensionality reduction (e.g., PCA, t-SNE), and large-scale data processing methods is a plus.
• Experience with SQL and data pipeline tools (e.g., Apache Spark, Airflow) is a plus.
• Understanding of biomanufacturing processes, particularly in cell culture, fermentation, or bioreactor operations.
• Ability to apply data science techniques to real-world challenges in a bioprocessing environment.
• Strong communication and collaboration skills across technical and scientific teams.
• Ability to work independently and proactively in a fast-paced, research-driven environment.
• Eagerness to learn new concepts and technologies related to data science and bioprocessing.

Company

Sanofi is a global biopharma company focused on prescription drugs, vaccines, and treatments for chronic, rare, and infectious diseases. Founded in 1973, the company is headquartered in Paris, Ile-de-France, FRA, with a team of 10001+ employees. The company is currently Public Company.