Principal Scientist Evidence Generation - Princeton, NJ at dsm-firmenich | Princeton, NJ | $180K/yr – $260K/yr

Principal Scientist Evidence Generation - Princeton, NJ

Princeton, NJ (Hybrid)

$180K/yr – $260K/yrSenior Level10+ years expFull time

Posted 4 months ago

The other 99% submit and hope. You're about to do something different.

Architect data science leadership to build scalable multi-omics pipelines and evidence packages for health, nutrition, and consumer care initiatives.

Own end-to-end data ingestion, harmonization, and scalable analytics across cohorts.
Must-have: 10+ years post-PhD in computational biology or related field with production-grade pipelines.
Standout: Pioneering use of LLMs and AI tooling to generate hypotheses and support regulatory-ready evidence.

Architectural Vision: Direct the development of scalable pipelines for the ingestion and harmonization of massive, heterogeneous human cohort datasets. Lead the design and implementation of a standardized analytical framework that integrates high-dimensional data (diet, lifestyle, host-m microbiome omics, and clinical outcomes).
Decision Frameworks: Establish AI/ML-assisted multi-criteria scoring systems to prioritize ingredients based on novelty, biological relevance, and commercial viability.
Evidence Orchestration: Oversee the creation of comprehensive scientific evidence packages, ensuring that every data science output is grounded in biological plausibility and robust enough to withstand clinical scrutiny.
Cross-Functional Influence: Act as a key strategic partner to other Data Science groups, Life Science and other research organizations, as well as the business unit of Health Nutrition and Care. Ensure data science is integrated into the earliest stages of experimental design.
Innovation Catalyst: Champion the adoption of state-of-the-art AI tooling, including Generative AI and Large Language Models (LLMs), to revolutionize how the organization synthesizes knowledge and generates novel hypotheses.
Mentorship: Provide technical mentorship to junior data scientists, fostering a culture of systems-oriented thinking and code reusability.

PhD in Computational Biology, Bioinformatics, Biostatistics, Epidemiology or a related quantitative field with 10+ years of post-doctoral experience (predominantly in an industrial R&D setting).
Expert-level command of human molecular biology, with a focus on leveraging processed multi-omics and microbiome data for advanced analytics.
Familiarity with large-scale cohort data and the challenges of working with real-world evidence
Proven history of leading high-impact discovery, translational science programs and/or clinical programs that resulted in successful product launches or major scientific breakthroughs.
Deep expertise in Python/R and with a track record of building production-grade analytical frameworks.
A forward-thinking approach to using Large Language Models (LLM) for scientific knowledge extraction and automated hypothesis generation.
Understanding of metadata management and harmonization frameworks for large-scale longitudinal research data is a plus.
Comfortable operating at the complex intersection of data science & AI, human biology, and global research and development. Capable of distilling high-dimensional technical complexity into a clear, persuasive narrative for non-technical stakeholders.

A hybrid workplace that offers flexibility to employees across the business.
A broad variety of projects, data types, and statistical approaches, ensuring you never stop learning and can apply a wide range of methods.
A team of diverse, open-minded colleagues who aren’t afraid to think outside the box and challenge the status quo.
A truly global and collaborative team environment that cares about our employees’ experience and growth.
Unique career paths across health, nutrition and beauty - explore what drives you and get the support to make it happen.
A chance to impact millions of consumers every day – sustainability embedded in all we do.