* **Proprietary biological data at scale** — Access to one of the world's largest proprietary datasets of antibody sequences, structures, and functional annotations from decades of therapeutic development* **World-class compute infrastructure** — State-of-the-art GPU clusters and cloud resources for training large-scale foundational models* **Real therapeutic impact** — Your models will be validated against real targets and integrated into live drug discovery programs* **Scientific freedom** — We encourage publication, conference participation, and collaboration with leading academic labs* **Integral collaboration** — Work with interdisciplinary teams across computational biology, protein engineering, and therapeutic development* **Architect and train next-generation foundational models** for antibody and NANOBODY(R) design, including protein language models, structure prediction models, diffusion-based generative models, and multimodal architectures* **Push the boundaries of generative protein design** — develop novel training strategies, fine-tuning approaches, and inference methods that leverage Sanofi's unique biological data assets* **Bridge research and application** — deploy your models into production pipelines where they'll be used to design real therapeutic candidates against challenging targets* **Validate rigorously** — design benchmarking strategies and work with wet-lab teams to experimentally validate model predictions on therapeutically relevant targets* **Collaborate across disciplines** — partner with antibody engineers, structural biologists, screening teams, and therapeutic area experts to understand biological constraints and opportunities* **Stay at the cutting edge** — monitor emerging architectures and methods, evaluate their potential, and rapidly prototype new approaches* **Contribute to the scientific community** — publish your work, present at conferences, and help establish Sanofi as a leader in AI-driven biologics design* Ph.D. in computational life sciences, computer science, machine learning, bioinformatics, or related field (or M.Sc. with exceptional track record)* **Deep expertise in modern deep learning architectures** - transformers, diffusion models, flow matching, VAEs, or other generative modeling paradigms* **Hands-on experience training large-scale models** - you've trained models with millions to billions of parameters and understand distributed training, optimization strategies, and scaling laws* **Strong foundation in protein science** - understanding of protein sequence-structure-function relationships, ideally with focus on antibodies or therapeutic proteins* **Publication track record** demonstrating impact in foundational model development, generative modeling, and/or computational protein design* undefined* Expert-level Python programming and deep learning frameworks* Experience with ML/DL models for protein design (ESM, ProteinMPNN, RFdiffusion, AlphaFold, etc.) - training, fine-tuning, and application* Proficiency with distributed training frameworks and cloud/HPC environments* Software engineering practices - version control, testing, documentation, reproducibility* Familiarity with biological databases, sequence analysis tools, and structural biology software* Global, diverse, and inclusive team environment* Flexible working arrangements* Competitive compensation and benefits package
#J-18808-Ljbffr