Stony Brook University is seeking to support research and clinical laboratories by developing, optimizing, and porting biomedical data analysis pipelines, including those that employ artificial intelligence (AI) methods, to HIPAA-compliant and standard High-Performance Computing (HPC) clusters. This role involves significant data preparation, quality control, and analysis, and application of AI methods to contribute to cutting-edge biomedical research and clinical applications.
Requirements
- Experience in developing and implementing bioinformatics pipelines.
- Experience with programming languages and scripting (e.g., Python, R, Bash).
- Experience working with Linux systems.
- Experience working with HPC cluster environments, job scheduling systems (e.g., Slurm, PBS, Torque), as well as high-performance data processing frameworks such as Spark and Hadoop.
- Experience with HIPAA and PHI.
- Experience implementing and/or applying AI methods in biomedical data analysis.
- Experience working with containerization technologies (e.g., Docker, Singularity).
Responsibilities
- Develop, implement, and maintain statistical, machine learning, and AI pipelines and other informatics pipelines for biomedical data analysis.
- Optimize existing pipelines for performance, scalability, and reliability on HPC clusters.
- Port existing pipelines to HIPAA-compliant HPC environments, ensuring adherence to all regulatory and institutional data security policies.
- Deploy and manage pipelines on standard HPC clusters, adapting workflows as necessary to different computational environments.
- Perform comprehensive data analyses on biomedical data including multi-modal data analysis with genomics, imaging and clinical data and other high throughput biological data.
- Adapt and apply state-of-the-art AI methods for feature extraction, classification, and predictive analytics.
- Interpret and visualize complex biological data to support research and clinical decision-making.
Other
- Advanced Degree in Bioinformatics, Computational Biology, Computer Science, or a closely related discipline.
- Five (5) years of full time research experience in computational science.
- The Computational Scientist is expected to have problem-solving skills and be able to communicate effectively.
- Work closely with researchers, clinicians, and laboratory staff to understand computational needs and provide effective solutions.
- Provide training, documentation, and technical support to end-users on pipeline usage and best practices.
