Lausanne, Switzerland
Internship Explorer
Internship Explorer
At Debiopharm, every step we take is guided by one purpose: improving the lives of people affected by cancer and infectious diseases. As a privately-owned Swiss biopharmaceutical company, we’re driven by science, but above all, by the people behind every treatment — the patients and their families. Through our unique “development only” model, we bring forward promising therapies and transform them into treatments that can reach those who need them most, faster. Are you ready to be at the forefront of the model-informed drug development (MIDD)? Debiopharm International SA is seeking a highly motivated Research Fellow (Intern) to help build an AI-enhanced Quantitative Systems Pharmacology (QSP) platform. This project offers a unique opportunity to integrate preclinical, clinical data and real-world data with mathematical models and AI to accelerate the development of our Antibody-Drug Conjugate (ADC) pipeline. You will work directly on assets, bridging the gap between systems biology and data-driven decision-making. Research Fellow – AI-Enhanced Pharmacometrics (Intern) Location: Lausanne, Switzerland Department: Clinical Pharmacology & Pharmacometrics Project: 12-months internship Executive Summary of the Internship The primary mission of this fellowship is to develop and standardize a custom QSP platform for the Debiopharm ADC pipeline. By utilizing AI and advanced modeling techniques, you will contribute to a "Digital Twin" environment to simulate virtual trials, optimize dosing regimens, and establish "Go/No-Go" criteria. This role is central to a specific project strategy, aiming to shorten development timelines and enhance our proprietary MIDD capabilities. Key Responsibilities * QSP Data Integration: Contribute to integrating multi data source into the existing QSP platform for key ADC programs. * AI-Driven Modelling: Create templates for virtual population construction using AI and R to characterize populations of interest. * Simulator Development: Build virtual trial simulators using R or C++ for predicting compound efficacy and safety. * Decision Analysis: Develop R-based data analysis templates to define "Go/No-Go" criteria based on virtual trial simulations. * Documentation: Thoroughly document the development process and analysis workflows to ensure knowledge retention.
