The Khare Laboratory at Rutgers University invites applications for a postdoctoral fellow position in computational enzyme engineering and AI-based protein design. A primary project will focus on engineering DNA polymerases supported by a federally funded and multi-institutional collaborative effort on DNA polymerase engineering. Postdoctoral fellows are also encouraged and supported to develop independent research directions aligned with the lab’s scientific program. The laboratory develops and applies computational and machine-learning methods for enzyme engineering, de novo protein design, and the design of protein function. Research is conducted in close collaboration with experimental colleagues within and outside the group at Rutgers and beyond, with iterative cycles between computational design and experimental characterization. Position Status Full Time Posting Number 26 FA 0469 Posting Open Date 05/08/2026 Posting Close Date 07/31/2026 Qualifications Minimum Education and Experience - PhD (awarded or expected within six months of start date) in computational biology, bioinformatics, biophysics, chemistry, computer science, or a closely related field. Certifications/ Licenses Required Knowledge, Skills, and Abilities - Publication record (published, in press, or as a preprint) in protein design, protein engineering, computational structural biology, or machine learning for biology. - Demonstrated programming proficiency in Python, including experience with modern deep-learning frameworks (Py. Torch and/or JAX). - Submission of a representative code sample or link to a public code repository (e.g., GitHub) as part of the application. Preferred Qualifications - Direct experience with contemporary protein design tools and models (e.g., Rosetta, Protein. MPNN, R - Fdiffusion, Alpha. Fold-family models, ESM-based or other protein language models, or comparable methods). - Experience training or fine-tuning ML models on large experimental datasets. - Prior track record of close collaboration with experimentalists. Equipment Utilized Physical Demands and Work Environment Overview - Design, implement, and apply AI-based methods merged with molecular modeling for protein design and engineering, including one or more of de novo design, sequence (re)design, and design of functionally relevant properties such as substrate selectivity and catalytic activity, stability, enzyme complementation, and photocontrol. - Develop and train ML models informed by diverse experimental data such as (a) enzyme activity, specificity, and stability measurements; and (b) high-throughput sequencing data based on library screening and/or directed evolution. - Collaborate closely with experimentalists on design–build–test–learn cycles including analysis and design of libraries. - Prepare and publish manuscripts; present at conferences; contribute to grant-related reporting. - Mentor graduate and undergraduate trainees. Statement Posting Details