Postdoctoral Research Associate - Isayev Lab

Description

The Isayev Lab at Carnegie Mellon University is seeking a highly motivated postdoctoral associate to conduct cutting‑edge research in computer‑aided drug discovery. The successful candidate will develop and apply machine learning methodologies to accelerate drug discovery pipelines, with an emphasis on active‑learning‑guided optimization, virtual screening of ultra‑large chemical libraries, and the integration of computational predictions with experimental validation.

• Ph.D. in Computational Biology, Bioinformatics, Cheminformatics, Computational Chemistry, or closely related field
• Doctoral research focused on machine learning applications in drug discovery, molecular design, or computational pharmaceutical sciences
• Demonstrated expertise in active learning methodologies for molecular optimization

• Proven track record of first‑author publications in high‑impact peer‑reviewed journals
• Expertise in developing and implementing active learning or Bayesian optimization workflows for drug discovery applications
• Experience with binding free energy calculations (relative or absolute FEP, thermodynamic integration) for lead optimization

• Advanced proficiency in Python programming and modern machine learning frameworks (PyTorch, JAX, scikit‑learn, GPyTorch, XGBoost, or equivalent)
• Extensive experience with cheminformatics toolkits (RDKit, Open Eye Toolkit) and molecular modeling software (AMBER, OpenMM, or similar)
• Demonstrated competency in molecular docking methodologies (OEDocking, Autodock Vina, or equivalent) and structure‑based drug design
• Experience with high‑performance computing environments, and job orchestration systems (SLURM)
• Proficiency in Bayesian optimization and surrogate modeling techniques (Optuna, GPyOpt, or equivalent)
• Familiarity with workflow automation tools (Next Flow, or equivalent) is highly desirable

• Strong foundation in computational drug discovery, including virtual screening, hit identification, and lead optimization strategies
• Understanding of ligand‑protein interactions, binding affinity prediction, and structure‑activity relationships
• Knowledge of drug discovery campaign workflows from hit finding through lead optimization

• Demonstrated ability to work collaboratively at the interface of computational and experimental chemistry
• Strong written and verbal communication skills evidenced by publications and presentations
• Experience serving as a manuscript reviewer for chemistry or computational biology journals

• Experience with automated laboratory platforms, cloud laboratories, or high‑throughput experimental systems
• Track record of interdisciplinary collaborations bridging machine learning, computational modeling, and experimental validation
• Experience with ultra‑large chemical library screening or virtual library enumeration
• Familiarity with proteochemometric modeling or multi‑target drug design

Carnegie Mellon University is an equal opportunity employer. It does not discriminate in admission, employment, or administration of its programs or activities on the basis of race, color, national origin, sex, disability, age, sexual orientation, gender identity, pregnancy or related condition, family status, marital status, parental status, religion, ancestry, veteran status, or genetic information. Furthermore, Carnegie Mellon University does not discriminate and is required not to discriminate in violation of federal, state, or local laws or executive orders.