FSP Associate Manager, Safety Data and Systems - Pharmacovigilance

Thermo Fisher Scientific•Morrisville, NC

25d•Onsite

About The Position

Apply AI/ML and NLP methods to pharmacovigilance safety data within GxP-validated, explainable, and regulator-defensible frameworks. The role leads deliverables for GPS Safety Data Management and Safety System Maintenance and provides high-quality data outputs for Safety Signal Management, Risk Management, and Safety Evidence generation. It collaborates with client functions and vendors to support seamless GPS Safety Data and Systems operations. The position designs, develops, and validates AI/ML and NLP components for safety operations, including MedDRA/WHODrug auto-coding, case triage, duplicate detection, and narrative summarization, with human-in-the-loop checkpoints. It contributes to model lifecycle management and regulatory qualification of safety-relevant AI/ML solutions, and serves as a technical resource for configuring, maintaining, and administering Oracle Argus Safety. The role also supports system operations, troubleshooting, validation, testing, deployment, reporting, analytics, integrations, and audit readiness. The Associate Manager works with pharmacovigilance, clinical, regulatory, quality, internal systems, BIS/DT, and other client functions to ensure safety data management aligns with global regulatory standards. Responsibilities also include aggregate report and line-listing generation and quality control, procedural documentation, training, staying current on relevant regulations and PV technology guidance, and recommending process and tool improvements. Additional tasks and projects may be assigned by the line manager or delegate.

Requirements

Bachelor’s degree or country equivalent in computer science, data science, computational linguistics, applied statistics/biostatistics, life sciences, information technology, or another relevant field.
At least 3 years of proven experience with safety database systems such as ARGUS or ArisG, including workflow management.
Proficiency in Python for ML development, including scikit-learn, pandas, and NumPy, and experience with at least one deep learning framework such as PyTorch or TensorFlow.
Experience with NLP for extracting adverse events, drugs, and outcomes from unstructured text, including case narratives, medical literature, call transcripts, and spontaneous reports.
Knowledge of named entity recognition, relation extraction, and text classification.
Experience with transformer-based or large language models for narrative generation, summarization, and information extraction.
Experience with supervised and unsupervised methods for classification, clustering, and anomaly detection.
Knowledge of feature engineering and model evaluation, including precision/recall trade-offs, ROC/AUC, and calibration, and why recall and sensitivity are emphasized in safety contexts.
Experience with model lifecycle management using standard MLOps tooling, in line with client DT/BIS standards.
Model explainability and interpretability skills, such as SHAP or LIME, are essential.
Understanding of GxP/GAMP 5 validation as applied to AI/ML systems and model governance.
Working understanding of safety database data models such as Argus/ArisG and E2B(R3) structure.
Proficiency in electronic systems commonly used for Safety/PV, including systems for data visualization, analysis, and dashboards.
Solid understanding of quality management processes, metrics, and KPIs.
Good knowledge of relevant pharmacovigilance regulatory requirements and guidance documents, including those for Europe, the US, and Japan.
Proficiency in Microsoft 365 tools, including Excel, Word, PowerPoint, Teams, SharePoint, and OneDrive.
Advanced Excel skills and working proficiency in SQL for querying safety and operational datasets.
Ability to communicate effectively and collaborate successfully across functions and with vendors.
Fluent written and spoken English.
Ability to work independently with minimal oversight and prioritize effectively.
Ability to complete multiple complex deliverables within tight timelines.
Ability to function effectively in a team environment.
An equivalent combination of education and experience, or proven practical expertise in the required skills, may be considered.

Nice To Haves

Familiarity with, or ability to rapidly acquire, GVP and 21 CFR 314 concepts.
Exposure to large language models applied to unstructured clinical or safety text.
Prompt engineering and retrieval-augmented generation (RAG).
Experience with MLOps tools such as MLflow, Azure ML, or Databricks.
Understanding of emerging regulatory expectations for AI/ML, including the EMA reflection paper on AI and FDA guidance.
Proficiency in safety database systems such as Argus and knowledge of other applicable Safety/PV systems, such as E2B gateways and safety signal detection tools.

Responsibilities

Design, develop, and validate AI/ML and NLP components for safety operations, including auto-coding, case triage, duplicate detection, and narrative summarization, with human-in-the-loop checkpoints.
Contribute to lifecycle management of safety-relevant AI/ML models, including versioning, monitoring, drift detection, retraining, and documentation.
Support qualification of AI/ML solutions against regulatory expectations in partnership with Quality, DT/BIS, and GPS Signal Management.
Configure, maintain, and administer the Oracle Argus Safety system.
Support day-to-day operation and troubleshooting of safety systems.
Assist with safety system validation, testing, and deployment of updates.
Generate, validate, and customize safety reports and analytics.
Collaborate with pharmacovigilance, clinical, and regulatory teams to align safety data management with global regulatory standards.
Participate in change management processes to enhance safety system integrations.
Contribute to audit readiness, including system inspections, validation reports, and compliance documentation.
Collaborate with internal systems teams, BIS/DT, and safety vendors on safety data issues.
Generate and perform quality control of aggregate reports and line listings.
Initiate and contribute to procedural documents, including Safety Management Plans, SOPs, work instructions, job aids, forms, and templates.
Collaborate with client functions such as Medical Information, Data Management, Business Information Systems, and Quantitative Science on pharmacovigilance technical aspects, setup, and operation.
Keep up-to-date on applicable regulatory and PV technology guidelines and share relevant information within GPS and with clients.
Participate in training related to safety data management.
Review processes and tools proactively and suggest improvements and efficiencies.
Complete additional tasks and projects as assigned by the line manager or delegate.