Director of AI Research & Engineering

Nxera Pharma is establishing a new AI enabled discovery initiative to build a high throughput AI and physics driven GPCR discovery engine that augments our world class experimental capabilities and extensive proprietary structural and chemogenomic data assets originating from Heptares Therapeutics. This initiative sits within our newly formed Computational Sciences team alongside Research Informatics, Chem Informatics and Bio Informatics. AI is being deployed across the NxWave™ platform, trained on the industry’s most extensive proprietary GPCR structure–ligand dataset and paired with our curated chemogenomic library of GPCR focused small molecules.

Our mission is to unlock the vast untapped potential of G-protein-coupled receptors (GPCRs) using computational and experimental innovation to design first-in-class therapeutics across metabolic, neurological, immunological, and rare diseases.

As part of Nxera’s mission to redefine how new medicines are discovered and to fully leverage advances in AI, quantum mechanics and next generation data integration, we are seeking a Director of AI Research & Engineering.

We are seeking a visionary Director of AI Research to lead the design, development, and deployment of advanced AI and machine learning capabilities across Nxera’s discovery pipeline.

This role will accelerate the evolution of NxWave™, embedding AI throughout structure determination, ligand discovery, and translational biology. You will bridge data science, structural biology, and chemistry, transforming how Nxera generates, analyses, and applies biological knowledge.

• Help define and implement Nxera’s enterprise-level AI strategy to scale intelligent automation across discovery and design including:
• Algorithmic Innovation
• Drive the application and development of advanced AI methods, including:
• Generative models for de novo ligand and peptide design (e.g. diffusion models, VAEs, GANs, reinforcement learning).
• Protein structure prediction and conformational modelling using graph neural networks (GNNs) and equivariant transformers.
• Molecular property prediction via multitask learning, transfer learning, and self-supervised pretraining on molecular graphs.
• Active learning and Bayesian optimisation to prioritise compounds for synthesis and assay.
• Natural-language processing (NLP) and retrieval-augmented generation (RAG) for mining scientific literature and experimental reports.
• Multi-modal integration of structural, chemical, and biological data using embedding fusion and transformer-based architectures.
• Integrate with NxWave™
• Collaborate with computational chemists and biophysicists to integrate AI models with experimental pipelines such as cryo-EM, crystallography, and high-throughput screening.
• Data Infrastructure & Governance
• Oversee design of scalable data pipelines, model lifecycle management, and ML-Ops infrastructure for secure and reproducible research.
• Build and lead a high-performing AI research & engineering team, mentoring scientists and engineers to deliver impactful, production-ready models.
• Partner with global AI and cloud technology leaders to co-develop new discovery algorithms.

You combine deep technical expertise with a passion for translating AI breakthroughs into transformative medicines.

• PhD (or equivalent) in Computer Science, Computational Biology, Applied Mathematics, or related quantitative discipline.
• 5+ years of experience applying AI/ML to life sciences, drug discovery, or healthcare innovation.
• Proven leadership in developing and deploying deep learning or generative AI systems at scale.
• Proficiency in frameworks such as PyTorch, Tensor Flow, or JAX; and experience with cloud-native ML infrastructure (AWS Sage Maker, Vertex AI, Azure ML).
• Demonstrated understanding of chemoinformatics, molecular docking, free‑energy prediction, or structure‑based drug design workflows.
• Experience with co‑folding.
• Publications or patents in deep generative chemistry, protein design, or foundation models.
• Familiarity with graph transformer architectures, diffusion models, or LLMs for scientific reasoning.

• Lead the evolution…