Principal Scientist, Computational Chemistry

Deep Apple Therapeutics•South San Francisco, CA

About The Position

Deep Apple Therapeutics, part of the Apple Tree Partners (ATP) portfolio, is a Bay Area biotechnology company focused on accelerating drug discovery by integrating molecular docking and structural biology with advanced computer-aided drug design (CADD) technologies. Our state-of-the-art platform combines advanced computational modeling, large-scale compound docking, cryo-EM-based structural biology, and deep learning to drive the efficient identification and development of novel therapeutics. We are seeking an experienced Computational Scientist to support and advance our computational initiatives in virtual hit discovery and traditional CADD for our portfolio programs. You will join a collaborative team of computational chemists, data scientists, machine learning engineers and medicinal chemists to integrate deep learning models into our drug discovery pipeline. This role will enhance our virtual screening capabilities, optimize molecular design, and facilitate cross-functional collaboration to translate computational insights into viable therapeutic leads. The ideal candidate will bring more than five years of expertise in computational modeling and proven support of drug discovery teams.

Requirements

Ph.D. in Computational Chemistry, Cheminformatics, Bioinformatics, or a related field.
Minimum of 5 years of professional experience in computational modeling within the biotechnology or pharmaceutical industry, including at least 1–2 years in a computational program leadership role.
Strong track record in virtual hit discovery and/or CADD, with demonstrated success leading to IND-ready assets.
Proficiency in programming languages such as Python, with extensive experience in data analysis, machine learning pipelines, and high-performance computing.
Excellent communication skills, with the proven ability to translate complex technical concepts to non-expert audiences.

Responsibilities

Lead the implementation of virtual hit discovery, including ligand-based and structure-based modeling, on a program-by-program basis.
Deploy deep learning models, including generative AI for molecular design, to predict molecular properties, binding affinities, and ADMET profiles for portfolio programs.
Collaborate closely with biology, medicinal chemistry, and machine learning teams to validate computational predictions through iterative feedback loops to accelerate pipeline programs.
Drive strategic initiatives, including partnerships with academic institutions, technology companies, and CROs, to strengthen our virtual hit discovery capabilities.
Stay current with emerging technologies in computational chemistry and deep learning, incorporating them into our pipeline to maintain a competitive edge.
Manage project timelines, budgets, and resources while ensuring compliance with data integrity and intellectual property standards.