Computational Scientist

About the role

Join a team building the computational and biological foundation for a toxicity prediction platform. This role involves exploring and analyzing large, diverse toxicity datasets to identify biological signals, improve predictive models, and shape new assays. You will contribute to developing AI systems that explain mechanisms and guide drug design.

Key facts

What you'll do

• Lead the exploration and analysis of extensive multimodal toxicity datasets, including imaging, transcriptomics, proteomics, and functional cellular readouts.
• Pinpoint subtle biological indicators that differentiate safe from toxic compounds across human systems like liver, heart, kidney, and immune biology.
• Transform noisy, high-dimensional experimental data into clear biological insights, robust features, quality metrics, and datasets ready for modeling.
• Analyze high-content imaging and transcriptomic data from primary human hepatocytes and multicellular hepatic systems, focusing on phenotypes such as mitochondrial dysfunction and ER stress.
• Conduct detailed model error analyses to understand model performance, identify failures, and determine needs for new data or assays.
• Collaborate with machine learning researchers to enhance models that predict human toxicity based on dose, exposure, chemical structure, and biological response.
• Develop computational methods for extracting meaningful signals from imaging, transcriptomic, proteomic, and biochemical assays.
• Design and improve quality control systems for large-scale, high-throughput biological datasets.
• Work closely with wet lab scientists to optimize new assays for both biological plausibility and predictive modeling.
• Partner with pharmaceutical and biotech teams to interpret molecule toxicity profiles and clarify the biological basis of model predictions.
• Help innovate the future of computational toxicology, creating AI systems that explain mechanisms, reason over evidence, and guide drug design.

Requirements

• Strong background in both biology and computation.
• Ability to find meaningful signals within complex biological data.
• Keen scientific judgment to distinguish genuine biological insights from noise or artifacts.
• Interest in high-content imaging, transcriptomics, assay development, and building large experimental-to-clinical datasets.
• Commitment to data quality, reproducibility, and scientific rigor.
• Understanding of how experimental design, assay biology, feature extraction, and modeling choices interact.
• Eagerness to work across various biological systems and mechanisms, including hepatotoxicity, mitochondrial toxicity, and immune-mediated toxicity.
• Desire to contribute to real-world scientific problems rather than solely academic publications.
• Ambition to help build a foundational company from its early stages.

Skills & tools

• Python, Pandas, NumPy, SciPy, scikit-learn, Jupyter notebooks
• Statistical analysis, curve fitting, dose-response modeling, dimensionality reduction, clustering, classification, regression, model evaluation
• High-content imaging analysis, microscopy, morphology profiling, image-based phenotyping
• CellProfiler, Cellpose, napari, OpenCV, scikit-image, or similar image analysis tools
• Transcriptomics, proteomics, mass spectrometry, ADME, or other high-dimensional biological datasets
• High-throughput screening, assay development, automation, experimental QC
• Biological interpretation of model outputs and error modes
• Scientific communication: translating complex analyses into clear, credible narratives