Senior Computational Biologist

📋 Description

• • Architect and deploy multi-scale computational models that fuse machine-learning, mechanistic (ODE/PDE), and hybrid frameworks to predict how DNA and protein sequences translate into therapeutic performance, cell-line productivity, and product-quality attributes.
• • Build predictive models that map nucleotide and amino-acid sequences to functional outcomes such as transgene expressibility, secretory efficiency, aggregation propensity, thermal stability, and critical quality attributes for antibodies, AAV vectors, and other biologics.
• • Design and validate dynamic models of gene-regulatory networks, metabolic flux, and cell-population dynamics using time-course omics data (RNA-seq, ATAC-seq, proteomics, metabolomics) to simulate and optimize mammalian cell behavior in bioreactors.
• • Partner daily with wet-lab scientists to co-design experiments—leveraging Bayesian optimization, active learning, and other adaptive design strategies—to generate maximally informative data and accelerate model convergence.
• • Integrate high-dimensional NGS datasets with bioprocess metadata (pH, dissolved oxygen, metabolite profiles) to create digital-twin representations of manufacturing runs, enabling in-silico scenario testing and real-time process control.
• • Contribute to Asimov’s long-term computational roadmap by scouting and prototyping novel algorithms (graph neural networks, transformer-based sequence models, stochastic differential equations) that push the boundaries of synthetic-biology design.
• • Translate complex model outputs into actionable genetic design rules, feeding directly into our CAD platform and cell-engineering pipelines to reduce experimental cycles and increase first-pass success rates.
• • Publish and present findings at top-tier conferences (RECOMB, ISMB, AIChE) and in peer-reviewed journals, reinforcing Asimov’s reputation as a thought leader at the intersection of biology and computation.
• • Mentor junior computational scientists and cross-functional team members, fostering a culture of rigorous data science, reproducible code, and open scientific discourse.
• • Continuously refine data infrastructure and modeling workflows (Python, TensorFlow/PyTorch, Stan, AWS/GCP) to ensure scalability, traceability, and seamless integration with our cloud-based design platform.