Forward-Deployed ML Engineer – Cofolding

Stack

Responsibilities

• ▹Build and implement ML applications in structural biology, particularly fine-tuning and extending foundation models like OpenFold, Boltz-2 and ESMFold
• ▹Design model extensions for tasks such as protein complex and binding affinity prediction, including data distillation, benchmarking and evaluation pipelines
• ▹Define data preprocessing, selection and benchmarking strategies with customers and academic partners for novel training tasks involving protein structures, complexes and multimodal biological data
• ▹Carry out case studies providing scientific and technical expertise to customers, from scoping through to results delivery
• ▹Design, build and maintain scalable ML models and the pipelines for training, inference and production deployment
• ▹Collaborate cross-functionally so that models address real-world drug discovery needs
• ▹Contribute to publications or open-source work where relevant
• ▹By month 3: build a deep understanding of the Apheris product and current structural biology use cases; contribute to at least one customer-driven cofolding project
• ▹By month 6: build a customer-ready package for results analysis, work with the privacy team on model reverse-engineering risk, drive adoption of Apheris-generated models with customers
• ▹By month 12: own a customer-driven cofolding model development stream

Requirements

• ▹Deep experience building and training contemporary models in production at scale (e.g. AlphaFold, OpenFold, Boltz) and familiarity with modern MLOps tooling
• ▹Experience applying ML to real-world protein structure or drug discovery problems
• ▹Comfortable working in a fast-paced startup environment on customer-driven projects
• ▹Understanding of the technical challenges of structural biology and ability to design scalable data preprocessing, training and evaluation workflows

Nice to have

• ▹Experience in federated learning, privacy-preserving ML or privacy-preserving model training
• ▹Publications in ML or biology journals and conferences (e.g. NeurIPS, ICML, Nature Methods, Bioinformatics)

Soft skills

What we offer

• ▹Industry-competitive compensation, including early-stage virtual share options
• ▹Remote-first working, from home or a co-working space
• ▹Wellbeing budget, mental health benefits, work-from-home budget, co-working stipend, learning and development budget
• ▹Regular team lunches and social events
• ▹Generous holiday allowance
• ▹Quarterly all-hands meet-up at the Berlin HQ or another European location
• ▹A diverse, mission-driven team
• ▹Plenty of room to grow and shape your own role

About the company

Apheris powers federated life sciences data networks in which pharmaceutical companies collaboratively train higher-quality ML models on their combined proprietary data, while data ownership and control stay with the data custodians.