Senior AI/ML Data Scientist

The Computational Toxicology group within the Nonclinical Drug Safety (NDS) division at our company is actively seeking an AI/ML data Scientist to contribute to the discovery and development of effective, safer therapeutics for patients. This key role will be instrumental in supporting NDS’s broader mission to be at the forefront of AI/ML application and data science methodologies towards drug safety prediction. The ideal candidate will possess a strong foundation in Artificial Intelligence (AI)/Machine Learning (ML) and will be integral to the development of predictive ML models for safety and toxicology endpoints, using a variety of data modalities from drug discovery, preclinical development, clinical trials, and post-market surveillance. The candidate will implement AI methodologies to enable early safety hazard identification, generate viable hypotheses for mechanistic toxicology, and ensure the early adoption of these models into our company’s discovery and development pipeline.

Note: This position is available in West Point, PA; Boston, MA; or South San Francisco, CA.

Key Job Duties:

• Inform prioritization for in vitro and in vivo preclinical toxicology resources applying probabilistic, neural networks ML models, and generative AI methods.
• Utilize LLM and Generative AI approaches to generate hypothesis for mechanistic toxicology.
• Work collaboratively with colleagues across multiple sites and functional areas to deploy, utilize, and increase the visibility of ML approaches in selection of chemical series with a high probability of success, and/or enable prioritization of in vivo resources.
• Upscale NDS staff on the utility of predictive AI/ML approaches in drug safety
• Stay abreast with new AI approaches and regulatory landscape in the field of predictive toxicology.

Education:

• Master’s (with 4+ years) or Ph.D. in computer science, computational biology, cheminformatics, biomedical engineering, and related data science fields and relevant experience

Required Experience And Skills:

• Fluency in python, R programing, standard python packages like pandas, numpy, matplotlib, and ML frameworks such as TensorFlow or PyTorch
• Experience with various statistical ML techniques, including both supervised, and unsupervised learning as well as DNN architecture is required. First-hand experience using Generative AI and LLM methods in related data science field would be advantageous.
• Experience with version control and related code reproducibility practices such as git, documentation
• Self-motivated with a high level of autonomy
• High interpersonal skills with a collaborative mindset

Preferred Experience And Skills:

• Prior experience with high-performance or cloud computing environments (e.g., AWS) and data lake platforms (e.g., Databricks) plus
• Experience with machine learning (ML) models deployment frameworks such as MLOps plus

NOTICE FOR INTERNAL APPLICANTS

In accordance with Managers’ Policy – Job Posting and Employee Placement, all employees subject to this policy are required to have a minimum of twelve (12) months of service in current position prior to applying for open positions.

If you have been offered a separation benefits package, but have not yet reached your separation date and are offered a position within the salary and geographical parameters as set forth in the Summary Plan Description (SPD) of your separation package, then you are no longer eligible for your separation benefits package. To discuss in more detail, please contact your HRBP or Talent Acquisition Advisor.