Computational Biologist – Deep Learning

About the position At Syngenta, we believe every employee has a role to play in safely feeding the world and taking care of our planet. To support that challenge, the Bioinformatics group is seeking a Computational Biologist to help design, build, and deploy Artificial Intelligence models (e.g., deep learning) to analyze genomics data for crop improvement. The position is in Durham, North Carolina. Role Purpose: Work in a team of computational biologists to train, modify and apply deep learning models, and to create or enhance workflows that leverage these models in our seeds pipeline Join cross-functional diverse research teams to deliver the next generation of predictive and generative technologies to support Syngenta Seed’s product pipeline Become an active member of the Bioinformatics group and drive innovation in a rapidly evolving scientific discipline Synthesize results and clearly communicate progress and challenges to project team members

Responsibilities

• Assist in the design, building, and implementation of advanced predictive AI models using genomics data (gene expression, proteomics, epigenetics)
• Data preparation for internal machine learning and deep learning (ML/DL) projects, including data QC, basic statistical analysis, preprocessing, etc.
• Identification and organization of public and internal data sources for DL, based on specified use cases
• Exploration and implementation of cutting-edge model architectures available in the public domain
• Modification of existing DL model architectures to support new use cases
• Development of workflows that utilize DL models to support cross-functional project teams
• Collaborate with cross-functional stakeholders to accelerate AI adoption in product pipelines by explaining model predictions, validating biological relevance, and demonstrating measurable improvements in trait prediction and candidate selection
• Prepare thorough documentation of model architectures, experimental findings, and validation metrics and deliver presentations to diverse stakeholders, including data scientists and biologists

Requirements

• PhD or MS with experience in Deep Learning, Bioinformatics, Genomics, Computational Biology, or closely related area
• Strong understanding of plant or plant-pest/pathogen biology, gene regulation, and genomics
• Applicants must be familiar with LLM concepts and popular LLM architectures
• Excellent communication skills and the ability to work in a highly dynamic and collaborative environment
• Experience working with biological and multi-omics data
• Proficiency in the use of UNIX/Linux and its command-line environment
• Proficiency coding in Python
• Experience with PyTorch, TensorFlow/Keras,or JAX
• Experience with deep learning model creation, fine-tuning, hyperparameter optimization, and model deployment
• Knowledge/experiences in using LLMs (Transformers, Mamba, etc)
• Proficiency in grid computing (e.g. Univa, Slurm, etc.)
• Familiarity working with version control systems (e.g. Git, CVS, SVN,etc)
• Experience with Jupyter notebooks and conda environments

Nice-to-haves

• Experience with MLOps tools (e.g. MLflow)
• Experience with cloud computing with AWS
• Biology knowledge
• Experience building/fine-tuning LLMs (transformers, Mamba, Hyena, etc)
• Experience in programming with Github-Copilot, AWS Q, or similar AI agents to enable rapid development

Benefits

• A culture that celebrates diversity & inclusion, promotes professional development, and strives for a work-life balance that supports the team members.
• Offers flexible work options to support your work and personal needs.
• Full Benefit Package (Medical, Dental & Vision) that starts your first day.
• 401k plan with company match, Profit Sharing & Retirement Savings Contribution.
• Paid Vacation, Paid Holidays, Maternity and Paternity Leave, Education Assistance, Wellness Programs, Corporate Discounts, among other benefits.

Apply tot his job Apply To this Job