Postdoctoral Research Fellow

University of British Columbia • Vancouver, BC

9d • CA$70,000 - CA$80,000 • Onsite

About The Position

The Uterine Health Research Lab at UBC, led by Dr. Aline Talhouk, is a data-driven research group working at the intersection of uterine health, gynecologic oncology, computational biology, clinical informatics, and artificial intelligence. The lab develops and applies innovative data science and AI approaches to improve cancer prevention, diagnosis, treatment decision-making, and patient outcomes, with a growing focus on personalized medicine and AI-assisted clinical decision support. Our research integrates clinical, molecular, and real-world data with emerging computational approaches, including large language models, predictive modelling, and multi-omics data integration. The lab coordinates and contributes to large-scale national and international research initiatives and works closely with clinicians, computational scientists, and patient partners to translate research findings into clinically meaningful tools. The research team is also part of BC's Gynecologic Cancer Initiative, a world-leading interdisciplinary team working together to drive innovative research that transforms how we prevent, diagnose, treat, and improve survivorship care for people with gynecologic cancer. We are seeking a highly motivated Postdoctoral Fellow with a strong background in health data science, bioinformatics, or artificial intelligence to join the Uterine Health Research Lab. This position offers a unique opportunity to develop and deploy AI-powered analytics infrastructure across gynecologic cancer research initiatives. The fellow will lead the development of multi-omics data integration, interactive visualization tools, and AI-assisted clinical decision support tools for gynecologic cancers. The fellow will be supervised by Dr. Aline Talhouk and other co-investigators and senior lab members, with access to an international network of clinical and scientific collaborators.

Requirements

• PhD in computer science, clinical informatics, statistics, or a closely related field, conferred within the past five years.
• Demonstrated experience in health data visualization, interactive dashboard development, or clinical data tool design.
• Excellent programing skills (e.g., Python, R), with hands-on experience in Bash scripting, workflow management (Snakemake), LLMs, text mining, or knowledge graph construction (e.g., LangChain, Hugging Face, Neo4j, or equivalent).
• Experience benchmarking computational tools and interpreting performance metrics.
• Experience with structured and unstructured data, including parsing and processing large document corpora.
• Strong understanding of machine learning or AI methods applied to health or biomedical data.
• Demonstrated ability to assess model outputs, identify gaps, and iteratively refine analytical approaches.
• Excellent written and oral communication skills, including experience contributing to manuscripts or scientific reports.
• Demonstrated ability to work independently and manage complex, multi-partnership projects.

Nice To Haves

• Experience with federated or distributed data systems, privacy-preserving analytics, or multi-site research infrastructure.
• Familiarity with large language models, retrieval-augmented generation, knowledge graphs, or digital twin modeling in a health research context.
• Experience with bioinformatics tools such as SNV calling using Mutect2, Strelka, LoFreq)
• Background in oncology, women's health, or rare disease research.
• Experience collaborating across multidisciplinary and international teams.
• Familiarity with data governance frameworks, research ethics, or data access and sharing agreements in a research context.

Responsibilities

• Develop an interactive visual dashboards and exploratory data analysis tools that enable hypothesis generation and pattern interpretation across multi-omics and clinical data.
• Design and develop an AI-powered analytics dashboard that synthesizes distributed aggregate outputs from an international multi-site research network, enabling clinician-ready interpretation of network-level findings across rare gynecologic cancer subtypes.
• Build and evaluate retrieval-augmented generation (RAG)-based large language models (LLMs) pipelines to extract key entities, relationships, and concepts from peer-reviewed literature, clinical trials, and treatment guidelines, and transform these into structured knowledge graphs encoding relationships among histotypes, biomarkers, therapies, and outcomes.
• Assess the accuracy, completeness, and usability of AI-generated outputs, iteratively refining pipelines and methods.
• Conduct iterative co-design with clinicians, member investigators, and patient partners to ensure usability and clinical relevance of developed tools.
• Contribute to manuscripts, grant applications, conference presentations, and knowledge translation activities.
• Mentor junior trainees and research staff within the lab.

Benefits

• benefits

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level
• Education Level: Ph.D. or professional degree