Generative is thrilled to be partnering with an AI-native TechBio company building a new generation of machine learning systems for understanding complex biological systems.
Biological data is noisy, high-dimensional and heavily shaped by the experimental process. The challenge is to build models that can separate genuine biological signal from artefacts — and turn large-scale experimental datasets into reliable scientific insight.
They’re looking for a Senior ML Research Engineer to develop novel ML models and the research infrastructure behind them, working across metagenomics, metabolomics, 16S and other multi-omic datasets.
This is a highly hands-on research role where you’ll own problems end-to-end — from hypothesis and dataset design through model development, rigorous evaluation and publication-quality research.
You’ll work across:
- Novel ML models for complex biological data
- Foundation models, pretraining and fine-tuning
- Representation learning across sequences, graphs and molecular data
- Rigorous evaluation of noisy real-world datasets
- Reproducible training and inference infrastructure
- Experimental design and collaboration with biological scientists
- GPU / cloud training and scalable ML systems
- Research leading towards publications and scientific breakthroughs
They’re particularly interested in strong ML researchers and engineers with experience building and shipping research-driven ML systems. A PhD, publications or equivalent evidence of independent research is valuable.
Direct biology experience is not essential. Experience with omics, sequencing, molecular data, generative models or scientific/healthcare datasets is a strong plus — but exceptional ML researchers from other domains where data is noisy, high-dimensional or difficult to model are also encouraged to apply.
The company is building a genuine ML Lab-in-the-Loop, where models inform experiments and experimental results continuously feed back into the models. The goal is to create a rapid cycle between data → models → experiments → learning.
If you’re an ML researcher who wants to work on fundamental problems in biological intelligence rather than incremental model optimisation, I’d be very interested in speaking.
#J-18808-Ljbffr…