Johnson & Johnson Innovative Medicine is currently seeking a Principal Scientist, Generative Deep Learning to join our In Silico Proteins team within the Therapeutics Discovery organization, with a preference for this individual to be located at one of our sites in Spring House, PA, or Cambridge, MA. Remote work options in the US may be considered on a case-by-case basis.
This role presents a great opportunity to spearhead our molecular design and simulation initiatives, supporting and accelerating our drug discovery and development pipeline of protein-based therapeutics while collaborating with a passionate team of scientists and engineers. Your work will be pivotal in building, evaluating, refining, and applying sophisticated computational approaches and infrastructures.
Key Responsibilities:
* Lead the development, refinement, and fine-tuning of generative models, such as RFDiffusion, ProteinMPNN, and EvoDiff to enhance our capabilities in protein design.
* Implement new structure-based protein design methods using the latest advancements in AI - including diffusion, flow-matching, Graph Neural Networks (GNNs), Variational Autoencoders (VAEs), and other deep learning architectures.
* Integrate Multi-Property Optimization techniques into various generative methods to improve the efficacy and specificity of target molecules.
* Employ contrastive learning techniques to improve model adaptability and performance, particularly in differentiating functional protein structures.
* Collaborate with multi-functional teams to translate sophisticated scientific challenges into actionable strategies and ensure the alignment of AI tools with scientific goals.
* Maintain up-to-date knowledge of the latest trends in AI/ML, particularly in generative and discriminative modeling techniques, evaluating their potential impact on our research and development efforts.
* Work with external innovation partners to collaborate on pioneering developments in generative protein design.
Qualifications:
* A PhD with 2+ years of experience in Computer Science, Data Science, Computational Biology, Bioinformatics or a related field, with a strong emphasis on machine learning is required.
* Validated expertise in the development and application of generative AI models, including deep learning architectures and techniques such as diffusion, VAEs, contrastive learning, GNNs, and Large Language Models (LLMs) is required.
* Proficient in scientific programming and software development, with expertise in Python or C++ and deep learning frameworks such as TensorFlow or PyTorch is required.
* Experience with high performance computing and cloud-based compute solutions such as AWS is preferred.
* Experience in applying ML methods to computational protein design or modeling is preferred.
* Outstanding communication and leadership skills, capable of leading innovative projects and encouraging a team towards ground breaking solutions is required.
* Familiarity with large datasets, understanding of data analysis workflows, and/or knowledge of querying languages such as SQL is preferred.
* Experience with powerful ML packages for protein modeling and design such as AlphaFold, RosettaFold, ESMFold, ProteinMPNN, RFDiffusion, Chroma, IgFold, EvoDiff, etc is preferred.
* Desire for continuous learning and the ability to identify, evaluate and deploy emerging algorithms, models, and ML architectures is required.
* Up to approximately 10% travel may be required.
Johnson & Johnson is an Affirmative Action and Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, age, national origin, or protected veteran status and will not be discriminated against on the basis of disability.
#J-18808-Ljbffr