Postdoctoral Research Associate - AI-driven Structure Analysis for Biological Discoveries

Brookhaven National Laboratory•Upton, NY

3d•Onsite

About The Position

Brookhaven National Laboratory’s National Synchrotron Light Source II (NSLS-II) seeks a Postdoctoral Research Associate for AI-driven Structure Analysis for Biological Discoveries for an on-site position in the Biological, Environmental and Planetary Science Division. Advance the frontiers of structural biology by developing AI-driven methods for interpreting complex crystallographic data. This role will enable new discoveries in protein function, ligand binding, and dynamics through scalable computational analysis. The ideal candidate would have a background and an interest in Computational Biology, Artificial Intelligence and Machine Learning. Join a team of scientists at the leading macromolecular crystallography beamlines and at the computing center and contribute to science projects at the interface between AI method development and large-scale research facilities.

Requirements

Ph.D. in computer science, computational biology, physics, or related field.
Expertise in machine learning or AI.
Experience with molecular dynamics simulations and computational workflows.
Ability to work in teams.
Demonstrated track record of publications in the field.
Candidates must have completed all degree requirements by the commencement of employment
After obtaining a PhD, eligible candidates for research associate appointments may not exceed a combined total of 5 years of relevant work experience as a post-doc and/or in an R&D position, excluding time associated with family planning, military service, illness or other life-changing events
The selected candidate must be able to obtain and maintain a DOE Uncleared Personal Identity Verification (UPIV) credential.

Nice To Haves

Experience with structural biology, 3D ML and biology specific AI models.
Experience with HPC and surrogate modeling.
Familiarity with workflow orchestration tools.

Responsibilities

Develop workflows to improve models and maps to optimize likelihood for ligand placement
Develop AI/ML methods for automated interpretation of crystallography data for optimal ligand placement.
Build and curate training datasets linking electron density maps and structural models.
Design and evaluate AI models for 3D structural data.
Develop workflows for time-resolved crystallography data processing.
Integrate molecular dynamics with AI/ML methods.
Benchmark protein foundation model performance and integrate them with experimental analysis pipelines.
Work collaboratively with domain scientists, beamline scientists, and computational scientists.
Document methods and results.