Scientist, Data Science, Computational Receptor Biology - Long Island City, NY

dsm-firmenich•Princeton, NJ

1d•$100,000 - $140,000•Onsite

About The Position

We are seeking a highly skilled data scientist specialized in cheminformatics, bioinformatics and machine learning. The candidate would join dsm-firmenich's Computational Receptor Biology team and work with a talented team of data scientists, chemists and biologists mapping our sense of taste and olfaction. Our team is at the forefront of leveraging protein and molecular AI in chemosensory receptor biology to uncover new possibilities in nutrition, health, and beauty for our clients and their customers. This role offers the opportunity to drive interdisciplinary science projects that integrate the latest advances in computational biology, deep learning and receptor science while working in close collaboration with leading domain experts.

Requirements

Masters, Ph.D. or similar experience in Computer Science, Bioinformatics, Chemistry, Structural Biology, AI, or a related field.
1+ years of additional academic or industrial work experience in ingredients, or small molecule discovery, ideally in the chemosensory biology field.
Strong grounding in receptor biology and functional assay data, with the ability to reason about biological relevance beyond raw predictions.
Hands‑on experience in cheminformatics and bioinformatics, including chemical standardization, annotation, and integration of complex libraries.
Practical experience applying machine learning to real, noisy biological datasets, including uncertainty‑aware or baseline predictive models.
Working knowledge of active learning, experimental design, or learning‑efficiency concepts in screening or discovery settings.
A collaborative, scientifically curious mindset, with enthusiasm for learning across modeling approaches and engaging regularly with experimental teams.
Proficiency in modern ML, python, good code management, and working with CI/CD pipelines.

Nice To Haves

Familiarity with good use of coding agents preferred.

Responsibilities

Build and curate high‑quality, model‑ready datasets from heterogeneous receptor screening data, including mixtures, natural products, and noisy biological readouts.
Integrate receptor biology, assay context, and chemical representations to support predictive modeling and biologically meaningful interpretation.
Design robust dataset splits, benchmarks, and evaluation frameworks (e.g., receptor‑aware, scaffold‑aware, temporal) to ensure reliable model assessment.
Support and execute active learning and experimental prioritization strategies, translating model uncertainty into concrete experimental recommendations.
Collaborate closely with experimentalists, ML scientists, physicists, and ingredient modeling partners to close the data → model → experiment → insight loop.
Apply modern software development and machine learning tools and practices in your daily work, including a high level of proficiency in python. Familiarity with good use of coding agents preferred.