Director of ML Research – AI Applications

About Apheris

• AI Structural Biology (AISB) Network: Pharmaceutical companies collaborate in the field of co-folding, structure-based binding affinity predictions and antibody design.
• ADMET Network: Pharmaceutical and biotech companies collaborate to improve small-molecule property prediction and expand to further drug modalities.
• Antibody Developability Network: Pharma partners collaborate to federate historical and purpose-built antibody developability datasets for secure ML training, without data leaving each partner’s environment.

About the role

What you will do

• Set up and lead the dedicated ML Research team within AI Applications, working alongside existing engineering teams andestablishingthe research mandate for the organisation.
• Design, enhance, and train foundation models at scale for structural biology and co-folding, addressing core challenges in protein interaction modelling and drug discovery. 
• Leverage large-scale proprietary structural biology and biophysical datasets to develop improved data pipelines and model architectures that capture geometric and physical priors. 
• Translate advances in structural biology ML and adjacent literature into practical modelling approaches for real-world drug discovery problems. 
• Lead cross-functional delivery across AISB, ADMET, engineering, product, and privacy teams, ensuring research outputs integrate into production workflows. 
• Collaborate with academic partners on co-folding and structural biology research, contributing to publications and presenting findings at leading conferences. 
• Represent Apheris in customer discussions and scientific forums, and help solve high-impact modelling problems across multiple pharma partners.
• Build and mentor a high-performing team of ML researchers and engineers over time.

What we expect from you

• Develop a deep understanding of the Apheris product, our current structural biology and ADMET initiatives, and the key scientific questions emerging from our networks. Define the initial research roadmap for AI Applications and begin hands-on work on the regularisation and generalisation of co-folding models. 

• Deliver initial results and customer-ready analyses for the first AI Applications workstreams, especially around co-folding model generalisation. Establish strong collaboration patterns across AISB, ADMET, engineering, privacy, and external academic partners. Clarify the capability and hiring plan for the team. 

• Lead a functioning ML Research team embedded within the broader AI Applications organisation, working across multiple initiatives at Apheris. Own a portfolio of applied research workstreams spanning co-folding and ADMET, and be recognised as a trusted technical authority in customer discussions, academic collaborations, and external scientific settings.

• You hold a postgraduate degree (PhD or MSc) in Computer Science, Machine Learning, Computational Biology, or a related field, and have 7+ years of relevant experience, including 3+ years in technical leadership. 
• You have strong experience applying machine learning to biological problems, particularly in structural biology (e.g. cofolding, protein modelling) or adjacent domains such as ADMET. 
• You have a proven publication track record in top-tier ML or computational biology venues (e.g. NeurIPS, ICML, ICLR, ISMB, RECOMB, or similar). 
• You have hands-on experience with modern ML systems (Python, PyTorch) and have worked with or extended large-scale models (e.g. OpenFold, Boltz, or similar). 
• You are comfortable operating as a player-coach: setting technical direction, leading teams, and contributing directly to modelling and experimentation. 
• You are effective in cross-functional and customer-facing environments and can translate ambiguous scientific problems into clear technical approaches.

• You have experience in early-stage biotech or in building ML systems or research functions from scratch. 
• You have experience training large models, including distributed training across GPU clusters or cloud platforms such as AWS, Azure, or Lambda. 
• You have strong ML Ops and machine learning infrastructure experience, particularly with Kubernetes-based workflows. 
• You have experience developing QSAR models with classical machine learning or deep learning methods. 
• You have experience writing Triton kernels or otherwise optimising model performance at the systems level. 
• You have experience in federated learning, privacy-preserving ML, or other multi-party training environments.

What we offer you

• Industry-competitive compensation, including early-stage virtual share options 
• Remote-first working – work where you work best 
• Wellbeing budget, mental health support, work-from-home budget, co-working stipend, and learning budget 
• Generous holiday allowance 
• Office Days at our Berlin HQ or a different European location (3x per year) 
• A high-calibre, execution-focused team with experience from leading organizations