Senior Machine Learning Research Engineer, Apheris

• You have a PhD or MSc in machine learning, computational biology, computational chemistry, bioinformatics, physics, or a related field, with at least 2 years of professional experience applying ML to scientific problems
• You have hands-on experience training, fine-tuning and extending deep learning models for molecular or protein structure modelling
• You are able to rigorously interrogate ML models, their training, and scientific benchmarks, and translate insights into impactful improvements
• You are an expert in Python and PyTorch, can produce reliable and clean code, and are comfortable with multi-GPU and distributed training
• You have deep familiarity with structural biology and protein–ligand data formats, quality metrics and tooling
• You proactively identify opportunities to contribute scientifically in order to impact the organizational goals

Desirable

• We are looking for a Senior Machine Learning Research Engineer to help drive the research and development of machine learning models for molecular and structural biology
• This is a hands-on role at the intersection of foundation models, structural biology, and federated learning. You'll execute research projects, turning ambitious scientific goals into frontier ML models that can be evaluated, released, and used in real drug-discovery workflows
• Develop and improve ML models in molecular and structural biology, such as co-folding and binding affinity models, for drug design applications and workflows, driving them from ideation through prototyping iterations to robust tooling
• Build effective benchmarking and evaluation strategies for model evaluation and iterate and refine existing modelling approaches based on data-driven insights
• Diagnose and resolve data quality and pipeline issues that affect model quality
• Stay up to date with a rapidly evolving research literature and identify best public approaches to aid in research and development
• Collaborate with customers, partner-facing engineers, and external collaborators to support real-world drug design use cases