Postdoctoral Fellow, Computational Genetic and Safety Data Science

Role Summary

In this cross-functional role, the postdoctoral fellow will develop AI-driven methodologies to bridge the gap between genomic evidence and safety outcomes, addressing a critical challenge in pharmaceutical development. This position sits at the intersection of artificial intelligence, human genetics, and safety assessment, supporting AbbVie's commitment to leveraging genetic insights to improve clinical success rates.

Responsibilities

• Identify, curate, and process internal and external genetic and safety-related datasets, applying sophisticated data science methodologies
• Design and implement agentic AI systems capable of autonomous data querying, extraction, and interpretation across traditionally siloed safety and genomic domains
• Develop advanced data harmonization techniques and standardized ontologies to enable integration of genetic, preclinical, and clinical safety datasets
• Implement graph-based retrieval-augmented generation (RAG) methods to enhance knowledge extraction and information synthesis
• Develop cross-pathway analytical methods using AI to predict safety outcomes for multiple targets and combination therapies
• Collaborate with research teams and data scientists to design data-driven strategies using machine learning/AI methods that support discovery and preclinical safety studies
• Generate and validate experimental hypotheses derived from AI models in collaboration with in vitro teams
• Publish research findings in peer-reviewed journals and present at scientific conferences

Qualifications

Basic Qualifications

• PhD in Computational Biology, Bioinformatics, Computer Science, Human Genetics, Toxicology, or related field (summer and fall graduates are also welcome to apply)
• Strong programming skills in Python with experience in data manipulation, analysis, and machine learning libraries
• Demonstrated experience in applying advanced AI/ML methods to biological problems
• Experience with database querying, management systems, and data extraction techniques for large datasets
• Knowledge of natural language processing (NLP) and/or large language models (LLMs)
• Experience with genomic data analysis, including variant interpretation or population genetics
• Proficiency in statistical analysis and interpretation of complex biological datasets
• Demonstrated ability to develop data visualization tools and interfaces for biological data representation
• Excellent communication skills, with ability to translate complex computational findings to diverse stakeholders
• Track record of scientific creativity and problem-solving in research activities

Preferred Qualifications

• Experience with agentic AI systems, prompt engineering, or multi-agent frameworks
• Familiarity with retrieval-augmented generation (RAG) and knowledge graph applications
• Experience with semantic search, ontology development, and cross-domain data integration
• Background in clinical safety, toxicology, or pharmacology
• Understanding of biological pathways and their relationship to disease mechanisms or drug response
• Experience with cloud computing environments and large-scale data processing
• Familiarity with topic modeling, semantic modeling, or other text mining approaches
• Experience working with large-scale genomic datasets (e.g., UKBB, FinnGen)
• Knowledge of in vitro safety assays and translational medicine concepts
• Publication history in relevant fields (AI/ML, genetics, toxicology)
• Experience with deep learning frameworks and generative AI models (e.g., GANs, VAEs)

Skills

• Artificial intelligence and machine learning
• Genomic data analysis
• Data harmonization and ontology development
• NLP and large language models
• Data visualization and communication of complex results
• Cross-functional collaboration and scientific writing