Senior Scientist, Computational Receptor Biology & Machine Learning - Long Island City, NY

DSM•San Diego, NY

15d•Hybrid

About The Position

Join us at the intersection of AI, biology, and sensory science. We are seeking an exceptional Machine Learning Researcher with deep expertise in deep learning architectures and distributed training systems to help push the boundaries of protein-ligand interaction modeling. As part of our Data Science Computational Receptor Biology team, you’ll collaborate with world-class data scientists, chemists, and biologists to decode the molecular mechanisms behind taste and smell. Working at the forefront of protein and molecular AI, you’ll develop next-generation models that accelerate scientific discovery and unlock innovative solutions in nutrition, health, and beauty. The Senior Scientist, Computational Receptor Biology & Machine Learning position is a unique opportunity to apply state-of-the-art machine learning techniques to complex biological challenges, contributing to groundbreaking research with real-world impact. You’ll play a key role in shaping interdisciplinary projects that combine advances in computational biology, large-scale deep learning, and receptor science while partnering with leading experts across scientific domains.

Requirements

Ph.D. or equivalent experience in Computer Science, Mathematics, Physics, Computational Biology or a related field
3-7 years of additional academic or industry experience developing novel architectures or training paradigms
Deep expertise in ML, applied mathematics, or physics ‑ inspired modeling, with strong intuition for geometry, symmetry, probabilistic inference, and learning dynamics
Hands ‑ on experience with modern deep learning frameworks (PyTorch and/or JAX) and ability to build non ‑ trivial models for structured or geometric data
Familiarity with generative or probabilistic modeling approaches (e.g., diffusion, flows, score ‑ based models, uncertainty estimation), even if applied outside biomolecular systems
A demonstrated ability and enthusiasm to learn new scientific domains quickly and collaborate with subject ‑ matter experts to apply ML in real discovery contexts

Responsibilities

Lead development of advanced deep learning models grounded in geometry, physics, and probabilistic reasoning, and apply them to receptor–ligand interaction problems
Design and adapt equivariant, multimodal, and/or generative architectures (e.g., diffusion, flows) for structured molecular and biological data, with openness to learning domain ‑ specific representations and constraints
Own scalable model training distributed across Graphics Processing Units (GPUs), evaluation, and iteration workflows, ensuring rigor, reproducibility, and measurable impact in discovery settings
Translate foundational machine learning (ML) ideas into practical receptor ‑ aware modeling tools, collaborating closely with domain experts to bridge theory and application
Contribute technical leadership and mentorship while working cross ‑ functionally with experimentalists, physicists, chemists, and ingredient modeling partners