Technical Lead – Large Molecule AI Systems

Accountabilities:

• Lead the development and delivery of federated large molecule AI systems across domains such as antibody modeling, protein co-folding, binder prediction, and biologics developability.


• Drive the implementation of large-scale biomolecular foundation models, including systems inspired by OpenFold, Boltz-2, and ESM, ensuring reliable and high-quality model releases.


• Translate ambiguous scientific and technical goals into structured execution plans, prioritization frameworks, and clearly defined workstreams.


• Define evaluation strategies, validate model performance, and ensure outputs meet production-grade standards for real-world drug discovery applications.


• Manage risks, dependencies, technical trade-offs, and delivery timelines, providing clear recommendations to stakeholders and leadership.


• Align consortium and cross-functional stakeholders on data requirements, objectives, evaluation criteria, and delivery expectations.


• Collaborate closely with product, engineering, research, and leadership teams to ensure model roadmaps align with application and business needs.


• Act as a player-coach, contributing directly to modeling, experimentation, and architecture decisions while mentoring senior engineers and ML scientists.

Requirements

• Advanced degree (PhD, MSc, or equivalent experience) in machine learning, computational biology, structural biology, or a related field.


• 5+ years of experience applying machine learning to complex biological or scientific problems such as antibody engineering, protein design, binder prediction, or drug discovery.


• Strong hands-on expertise in Python and PyTorch, with experience working on or extending large-scale models such as AlphaFold, OpenFold, Boltz, or ESM.


• Proven experience in ML system delivery, including evaluation, training, deployment, and validation of production-ready models.


• Solid understanding of ML infrastructure and MLOps practices, including Kubernetes-based training and distributed workflows.


• Demonstrated ability to lead end-to-end ML projects, define technical direction, and drive teams toward high-quality delivery outcomes.


• Strong capability to define success metrics, validate model quality, and ensure robustness for real-world applications.


• Experience operating in cross-functional environments involving research, engineering, product, and scientific stakeholders.


• Excellent communication skills and ability to turn ambiguous scientific challenges into clear, executable technical plans.


• Experience in federated learning, distributed training, or privacy-preserving ML is considered a strong advantage.


• Prior exposure to regulated, enterprise, pharmaceutical, or biotech environments is a plus.


• Publications in top-tier ML or computational biology venues are considered a strong asset.

• Competitive compensation package including virtual share options.


• Fully remote-first working model with flexibility across locations.


• Wellbeing budget and access to mental health support services.


• Home office setup allowance and co-working space stipend.


• Dedicated learning and development budget for courses, conferences, and certifications.


• Generous holiday allowance to support work-life balance.


• Periodic in-person collaboration sessions in European locations, including Berlin HQ.


• Opportunity to work with a high-caliber, execution-focused team operating at the forefront of AI and drug discovery innovation.

This listing is from ats_lever. View original listing ↗