FDA NAMs-Aligned
We are redefining human-centric drug testing through the convergence of 3D bioprinting, microfluidics, and AI. As an AI Scientist, you will build machine learning and multimodal systems that interpret biological complexity — from cellular images and biomaterial properties to molecular and omics data — enabling predictive, human-relevant drug discovery and safety testing.
Key Responsibilities
You will lead the development of AI models that connect experimental biology with computational prediction. Working alongside bioprinting engineers, data scientists, and molecular biologists, you will create the digital layer that transforms Z24 Bio’s tissue and organ-on-chip data into actionable insights.
- Develop and train deep-learning architectures (CNNs, Vision Transformers, multimodal networks) for imaging-based toxicity, morphology, and viability prediction.
- Build generative and self-supervised models to correlate 3D bioprinting parameters, bioink compositions, and tissue performance outcomes.
- Design AI pipelines integrating multi-omic, phenotypic, and sensor data to create predictive digital twins of organ models.
- Collaborate with experimental teams to standardize datasets, automate annotation, and ensure model interpretability.
- Implement uncertainty estimation, Bayesian inference, or active-learning strategies to guide high-value experiments.
- Deploy trained models into production and visualize outcomes through interactive dashboards for R&D and regulatory partners.
- Publish findings, contribute to IP filings, and represent Z24 Bio in conferences and collaborative AI-in-biotech initiatives.
Preferred Qualifications
We are looking for scientists who thrive at the intersection of computation and biology — thinkers who can turn data into discovery.
- PhD or MSc in Computer Science, Biomedical Engineering, Computational Biology, or related fields.
- 3+ years of experience in applied machine learning or deep learning for life-science data (imaging, time-series, omics, or text).
- Proficiency in Python and major ML frameworks such as TensorFlow, PyTorch, or JAX.
- Strong foundation in statistics, feature engineering, and model evaluation for unbalanced and noisy biological datasets.
- Experience in multimodal data integration (e.g., image + text, omics + phenotypic) and transfer learning.
- Familiarity with cloud-based ML pipelines, containerization (Docker), and collaborative code management (Git).
- Background or interest in biomedical imaging, drug discovery, or organ-on-chip data is a strong plus.
What We Value
Our foundation is built on the convergence of curiosity, ethics, and excellence. We believe that the future of healthcare innovation depends not just on the technologies we create, but on the values that guide how we create them.
01
Integrity
Every experiment is grounded in rigor, reproducibility, and transparency. We hold ourselves to the highest ethical standards in pursuit of human-relevant science.
02
Innovation
We thrive on asking “why not?” and explore the uncharted spaces where biology meets computation — transforming bold ideas into functional tissue systems.
03
Interdisciplinarity
We unite biology, engineering, and artificial intelligence—transforming cross-disciplinary insight into tangible breakthroughs.
04
Impact
Every printed tissue, every line of code, every experiment moves us closer to a world where drugs are tested safely, efficiently, and humanely — for the benefit of all.
Why Join Z24 Bio
Joining Z24 Bio means becoming part of a deep-tech movement that is transforming how the world discovers, tests, and delivers medicine. We’re not just building tissue models—we’re building the future of human-relevant science.
Every project you lead at Z24 Bio carries real-world impact—from bioprinted tissues that replace animal models to AI that predicts patient safety. Here, innovation isn’t confined to the lab—it drives ethical progress for humanity.
Global Collaboration
Work alongside scientists, engineers, and visionaries from top research institutions and technology hubs across the world.
