Computational Chemistry Intern - 2027

Computational Chemistry Intern, Summer 2027

Genesis Molecular AI is bringing together a world-class computational team to build the industry's fastest and most accurate small molecule property predictions by combining machine learning and physics-based methods. We are looking for early-career scientists who develop and apply computational chemistry and physics methods, increasingly with AI in the loop, to push forward our challenging drug discovery programs.

You will

• Work with a dedicated mentor on a focused research project that matches your interests and expertise and addresses a key challenge in our internal and partnered drug discovery programs.
• Develop and refine computational chemistry and physics methods. Potential project areas include quantum chemistry (DFT and wavefunction methods, QM/MM, torsional and conformational energetics, protonation and tautomer states), free energy simulations (relative and absolute binding free energies), and enhanced sampling (metadynamics, replica exchange, adaptive sampling).
• Collaborate with our machine learning team on molecular modeling and property prediction. Potential projects include machine-learned interatomic potentials (MLIPs) and hybrid ML/MM simulations, learned molecular representations, learned collective variables for enhanced sampling, generative models of conformational ensembles, protein-ligand co-folding and binding affinity prediction, and ADME property prediction.
• Work closely with our computer-aided drug discovery scientists and medicinal chemists to benchmark methods on real program data, test predictions prospectively, and integrate successful improvements into our drug discovery platform.

You are

• A PhD student with a proven track record of applying or developing computational chemistry and physics methods. Exceptional MS or advanced undergraduate students with substantial research experience are also encouraged to apply.
• Experienced in one or more areas of computational chemistry: quantum chemistry, free energy methods, enhanced sampling, molecular dynamics, or machine learning for molecular systems. Depth in one area matters more than breadth across all of them.
• Passionate about building methods that solve real problems, and rigorous about testing assumptions and validating results.
• A skilled programmer, preferably in Python, who can quickly turn research ideas into working code and assess the accuracy and reliability of the resulting methods.
• Experienced using AI coding agents to accelerate your work, with the scientific and engineering judgment to verify generated code, debug subtle failures, and recognize when results are physically wrong.