Postdoctoral Associate

About this position

• Postdoctoral Position in AI-Guided Focused Antibiotic and Prodrug Design
• The Reker Laboratory in the Department of Biomedical Engineering at
• Duke University is seeking a highly motivated and creative
• Postdoctoral Associate in computational chemistry, cheminformatics,
• and/or molecular machine learning to be part of an integrated
• computational and experimental team working to create focused
• antibiotic prodrugs that treat bacterial infections while sparing the
• gut microbiome. Our team develops artificial intelligence and machine
• learning approaches to design and optimize drug molecules. In this
• project, we aim to create small-molecule prodrugs that remain inactive
• outside the site of infection and are selectively activated in
• response to infection-associated environmental triggers. The
• successful candidate will develop predictive and generative molecular
• models to identify infection-responsive linker chemistries and
• optimize prodrug structures for properties including selective
• activation, intestinal absorption, stability, solubility, and
• microbiome sparing. A major emphasis of this position is prospective,
• experimentally driven molecular machine learning. Computationally
• designed molecules will be prioritized for synthesis and biological
• testing by collaborating experimental chemists and microbiologists,
• with experimental results rapidly returned to the computational team
• to guide subsequent design cycles. The position is therefore
• particularly well suited for a highly motivated, result-oriented
• scientist who is excited to see computational predictions translated
• into synthesized molecules and experimental outcomes, and who enjoys
• working closely as part of a team spanning computational and
• experimental disciplines. Duties and Responsibilities Design and
• perform computational research related to funded programs,
• specifically: Develop and evaluate predictive machine learning models
• for small-molecule and prodrug properties, including
• infection-responsive activation, metabolism, physicochemical
• properties, and ADMET. Develop and deploy generative molecular design
• approaches for infection-responsive linkers, prodrugs, and related
• small-molecule structures. Apply cheminformatics, molecular
• representations, structure-based modeling, and multi-objective
• optimization to prioritize experimentally actionable candidates. Work
• closely with synthetic chemists and microbiologists to design
• prospective experiments and incorporate experimental results into
• iterative design–synthesize–test–learn cycles. Analyze computational
• and experimental datasets and maintain reproducible computational
• workflows, code, and research records. Communicate research activities
• through reports, manuscripts, abstracts, presentations, and
• interdisciplinary project meetings. Contribute to the overall
• functioning of the research group and collaborative project, including
• mentoring graduate and undergraduate researchers and supporting a
• collegial and inclusive team environment. Qualifications By the start
• date, applicants should have a Ph.D. in computational chemistry,
• cheminformatics, chemical engineering, biomedical engineering,
• computer science, pharmaceutical sciences, chemistry, or a related
• discipline, with demonstrated experience applying computational
• methods to molecular problems. Strong candidates will have
• demonstrated expertise in one or more of the following areas:
• Molecular machine learning and deep learning Cheminformatics and
• molecular representations Generative molecular design Computational
• chemistry or structure-based drug design ADMET/property prediction
• Multi-objective molecular optimization Drug discovery or medicinal
• chemistry informatics Proficiency in Python and experience with modern
• machine-learning frameworks and cheminformatics tools are expected.
• Experience in organic/small-molecule synthesis, medicinal chemistry,
• microbiology, bacterial assays, or antibiotic research is advantageous
• but not required. Candidates should demonstrate strong communication
• skills, a record of independent research productivity, and enthusiasm
• for working both independently and collaboratively in an
• interdisciplinary, milestone- and goal-oriented research environment.
• We particularly encourage applicants who enjoy building computational
• methods that are prospectively tested in the laboratory, learning from
• experimental successes and failures, and rapidly translating those
• results into improved molecular designs. For more about the Reker
• Laboratory, visit: https://rekerlab.pratt.duke.edu/ Appointment
• Details Start date: October 2026 (flexible) Duration: The initial
• appointment is for one year, with the possibility of renewal by mutual
• agreement and subject to continued funding from a milestone-oriented
• sponsor. To apply: Email daniel.reker@duke.edu with a CV that includes
• a link to a public GitHub repository (or similar code portfolio)
• highlighting your previous work in molecular machine learning; a cover
• letter describing your research background, computational expertise,
• research interests, and professional goals; and contact information
• for three references. You will be contacted if we are interested in
• exploring your credentials further. Applications will be accepted
• until the position is filled.