Postdoctoral Research Associate - AI-driven Lab Automation for Life Sciences

About the role

The National Synchrotron Light Source II (NSLS-II) at Brookhaven National Laboratory seeks a Postdoctoral Research Associate for AI-driven Lab Automation for Life Sciences. The position aims to advance structural biology through AI-driven methods for improving crystal quality at scale.

Responsibilities

• Develop and implement AI-enabled laboratory workflows for automated crystallization screening, optimization, and characterization integrating imaging, experimental metadata, and diffraction outcomes.
• Design and deploy computer vision methods to detect and track crystal growth.
• Develop closed-loop optimization approaches to recommend crystallization conditions and harvesting strategies based on experimental feedback.
• Develop, train, and integrate AI/ML models with laboratory automation systems, including crystallization robotics, liquid handlers, and imaging platforms.
• Build scalable data pipelines linking experimental metadata, imaging data, and diffraction results for high-throughput analysis.
• Evaluate model performance using experimental metrics and support deployment into user-facing workflows.
• Collaborate with synchrotron beamline scientists and laboratory and crystallization staff.
• Document methods and results, contribute to manuscripts and reports, and present the work at conferences.
• Participate in interdisciplinary team science.

Requirements

• Ph.D. in computer science, bioinformatics, biophysics, applied mathematics, or related field.
• Expertise in machine learning, computer vision, or image analysis.
• Experience with data management and databases.
• Experience working with Python, scientific software development, version control and collaborative code development, such as Git.
• Ability to work in interdisciplinary teams.
• Strong publication record.

Preferred Knowledge, Skills, And Abilities

• Experience with machine learning frameworks (PyTorch, TensorFlow, etc.) and integrating ML in a research lab facility.
• Familiarity with lab automation or robotics.
• Experience with black-box optimization, including active learning or Bayesian optimization.
• Experience with imaging, time-series or high-dimensional data.
• Exposure to crystallography or structural biology.
• Experience with multimodal datasets and developing reproducible workflows.
• Familiarity with experiment tracking and metadata capture.