Hummingbird Bioscience

Intern, AI + Bayesian Decision Intelligence for Clinical Trial Modelling (Oncology)

Hummingbird Bioscience
BiotechSingapore, SingaporeOnsitePosted 2 months ago

About the role

AI summarised

Join Hummingbird Bioscience to build an AI-enabled Bayesian decision intelligence platform for oncology trials. This role applies advanced statistical and machine learning techniques to generate interpretable evidence, predict patient outcomes, and support critical decision-making in drug development.

BiotechOnsite

Key Responsibilities

  • Develop Bayesian models for primary and secondary endpoints, including credible intervals and posterior probabilities.
  • Implement ML models to predict response and safety based on baseline patient features/biomarkers.
  • Construct and justify priors informed by historical trials and Real-World Evidence (RWE), including sensitivity analyses.
  • Apply borrowing methods across similar diseases or patient subgroups to enhance modeling power.
  • Build ML pipelines for patient similarity matching and confounding adjustment when integrating external control arms.
  • Develop Bayesian dose-finding models to optimize dose selection balancing efficacy and toxicity.
  • Implement population PK and PK-ADA covariate modelling for exposure-adjusted safety and efficacy assessment.
  • Create an internal 'Clinical Insights Copilot' using LLMs to draft reports from modeling results.
  • Produce stakeholder-ready presentations explaining the clinical question, modeling approach, assumptions, key results, and recommended actions.

Requirements

  • Currently enrolled in a Bachelor’s or Master’s Program in a related quantitative field.
  • Strong proficiency in R for clinical statistics and reporting (tidyverse, stat libraries).
  • Familiarity with Bayesian modelling concepts: priors, posterior inference, operating characteristics via simulation, and sensitivity analyses.
  • ML experience in clinical outcome prediction (e.g., tree-based models, survival ML, calibration/validation).
  • Experience with modern AI tooling (LLM/RAG frameworks) and responsible data use.
  • Understanding of data privacy and security best practices for patient data.
  • Interest in oncology drug development and clinical/biostatistical approaches.
  • Excellent communication skills to present complex concepts clearly.