Lead Scientist - Large Molecules

About Apheris

At Apheris, we are building the future of how AI is applied in pharmaceutical R&D. We enable leading pharmaceutical teams to discover and develop drugs faster. We host the industry's largest federated data networks for drug discovery AI, spanning co-folding, ADMET, and antibody developability.

Across these networks, models are trained on proprietary industry datasets to achieve higher performance and broader applicability while keeping data control and IP protected. We deliver these superior models through drug discovery applications that enable teams to run them at scale, further customize them, and integrate them into existing R&D workflows.

• AI Structural Biology (AISB) Network: Top 20 pharma companies collaborate in the field of co-folding, structure-based binding affinity predictions and antibody design.
• ADMET Network: Top 50 pharma companies and biotechs 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

We're looking for a large molecule specialist to bring deep domain knowledge in antibody engineering, structural biology, and biologics to our networks. You'll help define the scientific workflows and modeling strategy for antibody-antigen co-folding, binder prediction, and developability prediction - working closely with our ML and engineering team, who own the actual model-building.

We need this person to give large molecules a real point of ownership at Apheris: someone who decides what's scientifically relevant as the network grows, and who partners can trust to speak with genuine drug-discovery credibility, not just AI credibility.

You don't need to write training code or build the models yourself. You do need enough AI/ML fluency to have a real, informed say in what gets built: sanity-checking results, catching where a modeling approach doesn't reflect biological reality, and helping translate scientific questions into a workable plan.

What you will do

• Define the scientific workflow, evaluation strategy, and benchmarking approach for our large molecule programs, including antibody-antigen co-folding, binder prediction, and antibody developability
• Use our own product as a hands-on user, and define user requirements for large molecule workflows so what gets built actually matches how scientists work
• Drive adoption of our large molecule models with pharma partners - helping them identify which programs and use cases they should be applied to, and supporting them in getting real value out of them
• Translate scientific and biological requirements from pharma partners into concrete inputs the ML/engineering team can build against
• Review model outputs and evaluation results against real structural biology / antibody engineering knowledge, flagging where something doesn't hold up biologically
• Represent Apheris's scientific perspective in partner conversations across our large molecule networks - aligning on objectives, evaluation criteria, and data requirements
• Stay current on the large molecule AI/ML landscape (OpenFold, AlphaFold, Boltz, ESM, antibody design/developability literature) enough to have informed opinions on modeling approach
• Work with product, ML, and engineering to make sure scientific requirements genuinely shape the roadmap, not just get bolted on afterward

What we expect from you

• You have a PhD, MSc, or equivalent experience, plus 5+ years in structural biology, antibody engineering, immunology, protein engineering, or a related biologics discipline
• You have real hands-on experience in antibody design, developability, or binder discovery - this is a domain-knowledge-first role
• You have some exposure to applying AI/ML to biological problems - you don't need to build models yourself, but you understand them well enough to contribute to a modeling workflow and judge whether outputs make sense
• You're comfortable partnering closely with ML/engineering teams and translating between biological reasoning and technical implementation
• You communicate clearly across scientific and technical audiences, and with pharma partner stakeholders

Nice to have

• You're familiar with OpenFold, AlphaFold, Boltz, or similar structure prediction tools
• You have experience with antibody developability assays, immunogenicity, or biologics manufacturability specifically
• You've worked directly with pharma partners or in a consortium/collaborative research setting
• You have a publication record in structural biology, immunology, or antibody engineering venues

What we offer you

• Competitive compensation with early-stage virtual share options
• Remote-first, with flexibility on work location
• Wellbeing support: mental health resources, work-from-home budget, co-working stipend, learning budget
• Generous holiday allowance
• Optional office days at Berlin HQ or another European location (roughly 3x a year)
• An execution-focused team with backgrounds from leading organisations