Technical Lead - Structural Biology Networks
This position is posted by Jobgether on behalf of a partner company. We are currently looking for a Technical Lead – Structural Biology Networks in the United Kingdom.
This is a high-impact technical leadership role at the intersection of structural biology, foundation models, and federated machine learning. You will lead the delivery of advanced AI model systems powering drug discovery networks used by leading pharmaceutical and biotech partners. The role combines deep hands-on technical execution with strategic leadership, turning complex scientific goals into production-ready model pipelines. You will define technical direction, guide architectural decisions, and ensure reliable, high-quality model releases that directly support real-world drug discovery workflows. Working across research, engineering, and product teams, you will help translate cutting-edge ML advances into scalable systems. This position is ideal for a leader who thrives in technically complex, fast-moving environments and enjoys bridging research and production at scale.
Accountabilities:
- Lead the end-to-end delivery of federated co-folding and structural biology model systems, staying deeply involved in modeling, architecture, evaluation, and engineering execution.
- Design, fine-tune, and extend large-scale foundation models for structural biology, including systems such as OpenFold, Boltz-2, and ESMFold, ensuring robust and production-ready outputs.
- Translate high-level scientific and technical objectives into clear execution plans, workstreams, and delivery milestones.
- Define and enforce model evaluation criteria, ensuring high-quality, validated results suitable for real-world drug discovery applications.
- Own delivery timelines and ensure model releases are shipped reliably, managing risks, dependencies, and technical trade-offs proactively.
- Align consortium and internal stakeholders on objectives, data requirements, evaluation frameworks, and delivery expectations.
- Collaborate closely with product, research, engineering, and leadership teams to ensure model development aligns with platform and customer needs.
- Mentor ML engineers and scientists while contributing directly to technical design, experimentation, and system architecture.
- Continuously surface and address blockers, bugs, and risks with clear, actionable recommendations.
Benefits:
- Competitive industry compensation, including early-stage virtual equity options.
- Remote-first working model with flexibility to work from anywhere.
- Wellbeing budget, mental health support, home office allowance, co-working stipend, and learning budget.
- Generous annual holiday allowance.
- Regular onsite team gatherings in Berlin or other European locations (approximately three times per year).
- Opportunity to work on cutting-edge AI systems applied directly to pharmaceutical drug discovery.
- High-caliber, execution-focused team with experience from leading global organizations.
Requirements:
- PhD, MSc, or equivalent experience in Machine Learning, Computational Biology, Computer Science, or a related field, with 5+ years of applied ML experience in complex scientific or biological domains.
- Strong hands-on expertise in structural biology ML, including protein modeling, co-folding, or binding prediction.
- Proven experience working with modern ML frameworks such as Python and PyTorch, and extending large-scale models like OpenFold, AlphaFold, Boltz, or ESM.
- Experience with MLOps or ML infrastructure, including Kubernetes-based training, evaluation, or deployment pipelines.
- Demonstrated ability to lead complex ML delivery projects, define technical direction, and drive teams toward production-quality releases.
- Strong player-coach capability, with experience mentoring technical teams while remaining hands-on in modeling and experimentation.
- Ability to translate ambiguous scientific problems into structured technical plans and execution roadmaps.
- Strong collaboration skills across research, product, engineering, and scientific stakeholders.
- Bonus: experience in federated learning, distributed training, or privacy-preserving ML environments.
- Bonus: experience in regulated or high-trust environments (pharma, biotech, enterprise ML systems).
- Bonus: publication record in top-tier ML or computational biology venues (NeurIPS, ICML, ICLR, ISMB, RECOMB, etc.).
