Senior Data Scientist

TraceLink•Wilmington, MA

8d•Onsite

About The Position

TraceLink is seeking a Senior Data Scientist in Wilmington, MA to lead the design and development of advanced machine learning and statistical models for pharmaceutical supply chain operations. This role involves architecting data pipelines, applying advanced analytical techniques, developing generative AI agents, implementing RAG pipelines, contributing to a data warehouse, and collaborating with cross-functional teams. The position also includes mentoring junior staff, evaluating new technologies, and communicating findings to leadership. The goal is to integrate data science and generative AI into customer-facing SaaS products within the life sciences ecosystem.

Requirements

Master’s degree (or foreign equivalent) in Computer Science, Data Science, Statistics, Mathematics, or a related field.
Three (3) years of professional experience as a Data Scientist or related role.
3 years of experience applying machine learning and advanced statistical methods including supervised/unsupervised learning, ensemble forecasting, causal inference, and predictive modeling to pharmaceutical or life sciences data.
3 years of experience in cloud-based deployment of machine learning products (AWS Sagemaker, Azure ML, or GCP AI/ML services), including deploying predictive models into production SaaS environments.
3 years of experience applying optimization, stochastic modeling, and queueing theory to supply chain or logistics problems, including forecasting drug shortages and supply disruptions.
3 years of experience with programming languages including Python, with applied use of SQL and distributed query engines for large-scale data retrieval and manipulation.
3 years of experience with data visualization and communication to present findings to senior stakeholders.
3 years of experience integrating AI/ML solutions into SaaS products or enterprise platforms in the life sciences domain.
2 years of experience with generative AI and large language models including fine-tuning and Retrieval-Augmented Generation (RAG), with application to knowledge graphs and pharma supply chain intelligence.
2 years of experience building or leveraging data warehouses for integrating diverse supply chain datasets, attaching metadata, and enabling advanced analytics and predictive ML.

Responsibilities

Lead the design and development of advanced machine learning and statistical models to support pharmaceutical supply chain serialization, track-and-trace, compliance analytics, and shortage prediction.
Architect scalable data pipelines and solutions using cloud-based platforms (AWS, Azure, or GCP) for processing large volumes of pharmaceutical supply chain and manufacturing data.
Apply advanced techniques in causal inference, optimization, stochastic modeling, and predictive analytics to tasks such as forecasting drug shortages and mitigate supply chain risks.
Develop, fine-tune, and deploy generative AI agents within Tracelink's Opus platform, enabling customers to interact with supply chain applications via autonomous, intelligent agents.
Implement advanced RAG (Retrieval Augmented Generation) pipelines to extract, connect, and query explicit and implicit relationships from large volumes of structured and unstructured pharma data.
Contribute to the design and implementation of a large-scale supply chain data warehouse that consolidates diverse data types and attached metadata for enabling advanced analytics and predictive ML solutions.
Collaborate with cross-functional product, engineering, and regulatory teams to translate complex business requirements into data science initiatives and deliver actionable insights.
Mentor and guide junior data scientists and data analysts in best practices for model development, validation, agent deployment, and ML product integration.
Evaluate emerging technologies, frameworks, and methodologies in AI/ML (including LLMs, agent frameworks, and predictive analytics) to continuously advance TraceLink’s data science capabilities.
Communicate results and recommendations to executive leadership, emphasizing business value, innovation, and alignment with global regulatory requirements.
Integrate data science and generative AI models into customer-facing SaaS products within the life sciences ecosystem.