Thomas Caulfield

I am a computational scientist and AI architect focused on drug discovery and molecular design, working at the intersection of generative modeling, physics based simulation, and quantum enabled computation. For more than 15 years, I have built systems that unify chemistry, biology, physics, and AI to accelerate molecular design, target characterization, and mechanistic insight across therapeutic areas. My expertise spans advanced AI systems, hybrid quantum classical workflows, and large scale biological modeling, with applications in small molecule drug discovery, toxicity prediction, and translational modeling. I design AI driven simulation and optimization pipelines and have hands on experience with IBM Quantum, Qiskit, AWS Braket, and IonQ, along with deep expertise in VQE, QAOA, UCCSD, Hamiltonian construction, noise aware modeling, resource estimation, and performance benchmarking. I design and deploy compute frameworks that integrate classical and quantum methods to accelerate therapeutic discovery across chemistry and biology. I build systems that combine classical and quantum compute to accelerate molecular energy estimation, structure function modeling, conformational search, generative molecular design, ADMET and toxicity prediction, and graph and sequence based biological inference. As the inventor or architect behind platforms such as Liquid Adaptive AI, QBM based architectures, LC JT VAE, and the Dynamicasome pathogenicity atlas, I focus on scalable, mechanistic, and data efficient learning systems that translate advanced computation into practical drug discovery impact. My background includes 10 years at Mayo Clinic as an Associate Professor and Director of cross disciplinary programs in computational biology, structural modeling, and AI enabled drug discovery and de novo molecular design. Current focus areas include AI driven and physics informed drug discovery, hybrid quantum classical simulation for chemistry and biology, generative molecular design, toxicity prediction, quantum inspired optimization and QBM architectures, multimodal biomedical modeling, GPU, QPU, and HPC infrastructure, and accelerated discovery platforms. Available for part time consulting and advisory roles in AI driven drug discovery, quantum enabled modeling, and scientific platform design. I help organizations architect discovery pipelines, evaluate advanced compute strategies, and build next generation simulation engines. I welcome inquiries from teams working on AI driven drug discovery, molecular design, and advanced computational modeling.