Princeton University
2025 Postdoctoral Research Associate - AI/machine learning for analytical and fo
Princeton University, Princeton, New Jersey, us, 08543
Overview
Position:
2025 Postdoctoral Research Associate - AI/machine learning for analytical and forensic chemistry The Skinnider Lab at Princeton University aims to recruit a postdoctoral fellow or more senior researcher to work on projects related to computational analysis of chemical and biochemical datasets. A major focus will be on the identification of small molecules from mass spectrometry-based metabolomics data, in part based on generative AI models of chemical structures. The position is available starting July 2025 and will remain open until excellent fits are found. The successful candidate will develop and apply computational approaches to chemical datasets, with artificial intelligence/machine learning (AI/ML) as a major focus. Many of the laboratory’s interests center around the identification of small molecules using mass spectrometry data, and the use of language models to predict the existence of undiscovered small molecules that are likely to be observed by mass spectrometry. Of particular interest for this position is the identification of emerging illicit drugs, also known as novel psychoactive substances, in seized drug products or clinical samples. The candidate will have the opportunity to work directly with experimentalists to validate predictions made by their machine-learning models, and to develop user-friendly tools that will be used by a broad community.
The scope of the work builds on recent publications from the laboratory, e.g. integrating language models with mass spectrometry data (https://www.nature.com/articles/s42256-021-00407-x, https://www.biorxiv.org/content/10.1101/2024.11.13.623458v1.abstract, https://www.nature.com/articles/s42256-024-00821-x, https://www.nature.com/articles/s42256-021-00368-1) or executing large-scale meta-analyses of mass spectrometric datasets (https://www.nature.com/articles/s41592-021-01194-4). The research is computational in nature but involves close interactions with experimental collaborators. Many of the problems are constrained by inherently low-quality or noisy data, and the successful candidate will be enthusiastic about contributing to data preprocessing and curation in addition to model development and evaluation. This opportunity will prepare candidates for a range of competitive positions in academia or industry that involve computational biology/chemistry, machine-learning for biological or chemical data, and drug discovery/design. Mentorship is taken seriously and every effort will be made to ensure the candidate is able to achieve goals in the next stage of their career. The successful candidate will be motivated, independent, and have strong written communication skills.
Responsibilities
• Develop and apply computational approaches to chemical datasets with a focus on AI/ML. • Work on identification of small molecules from mass spectrometry data and use language models to predict undiscovered molecules likely observed by MS. • Identify emerging illicit drugs (novel psychoactive substances) in seized drug products or clinical samples. • Collaborate with experimentalists to validate model predictions. • Develop user-friendly tools for use by a broad community. • Contribute to data preprocessing and curation alongside model development and evaluation. • Engage in large-scale meta-analyses of mass spectrometric data when applicable.
Qualifications
• PhD (or expected) in computational biology/chemistry, biochemistry, computer science, biological or chemical engineering, forensic science, or a related field. • Experience in one or more of the following areas demonstrated through at least one first-author publication: computational biology/bioinformatics, cheminformatics, analytical chemistry/mass spectrometry/metabolomics, or machine learning/computer science. • Track record of independence, motivation, and strong written communication skills. • Ability to work with noisy data, data preprocessing, and model evaluation. • Experience with AI/ML for chemical/biological data is desirable.
Term, Location, and Application
Term of appointment is based on rank. Postdoctoral positions are typically one year with potential renewal pending satisfactory performance and continued funding; more senior hires may have multi-year appointments. The work location is in-person on campus at Princeton University and is subject to Princeton University’s background check policy. To apply online, please visit the Princeton academic positions page and submit a CV and cover letter. The cover letter should highlight 1–3 publications or preprints that address the required experience, and include contact information for three references. Qualified candidates who pass an initial screening may be provided with short programming exercises to assess their skills. Only suitable candidates will be contacted.
Compensation and Benefits
Expected Salary Range: $65,000 - $70,000. The University offers a comprehensive benefits program to eligible employees. Please see the University benefits information for more details.
#J-18808-Ljbffr
Position:
2025 Postdoctoral Research Associate - AI/machine learning for analytical and forensic chemistry The Skinnider Lab at Princeton University aims to recruit a postdoctoral fellow or more senior researcher to work on projects related to computational analysis of chemical and biochemical datasets. A major focus will be on the identification of small molecules from mass spectrometry-based metabolomics data, in part based on generative AI models of chemical structures. The position is available starting July 2025 and will remain open until excellent fits are found. The successful candidate will develop and apply computational approaches to chemical datasets, with artificial intelligence/machine learning (AI/ML) as a major focus. Many of the laboratory’s interests center around the identification of small molecules using mass spectrometry data, and the use of language models to predict the existence of undiscovered small molecules that are likely to be observed by mass spectrometry. Of particular interest for this position is the identification of emerging illicit drugs, also known as novel psychoactive substances, in seized drug products or clinical samples. The candidate will have the opportunity to work directly with experimentalists to validate predictions made by their machine-learning models, and to develop user-friendly tools that will be used by a broad community.
The scope of the work builds on recent publications from the laboratory, e.g. integrating language models with mass spectrometry data (https://www.nature.com/articles/s42256-021-00407-x, https://www.biorxiv.org/content/10.1101/2024.11.13.623458v1.abstract, https://www.nature.com/articles/s42256-024-00821-x, https://www.nature.com/articles/s42256-021-00368-1) or executing large-scale meta-analyses of mass spectrometric datasets (https://www.nature.com/articles/s41592-021-01194-4). The research is computational in nature but involves close interactions with experimental collaborators. Many of the problems are constrained by inherently low-quality or noisy data, and the successful candidate will be enthusiastic about contributing to data preprocessing and curation in addition to model development and evaluation. This opportunity will prepare candidates for a range of competitive positions in academia or industry that involve computational biology/chemistry, machine-learning for biological or chemical data, and drug discovery/design. Mentorship is taken seriously and every effort will be made to ensure the candidate is able to achieve goals in the next stage of their career. The successful candidate will be motivated, independent, and have strong written communication skills.
Responsibilities
• Develop and apply computational approaches to chemical datasets with a focus on AI/ML. • Work on identification of small molecules from mass spectrometry data and use language models to predict undiscovered molecules likely observed by MS. • Identify emerging illicit drugs (novel psychoactive substances) in seized drug products or clinical samples. • Collaborate with experimentalists to validate model predictions. • Develop user-friendly tools for use by a broad community. • Contribute to data preprocessing and curation alongside model development and evaluation. • Engage in large-scale meta-analyses of mass spectrometric data when applicable.
Qualifications
• PhD (or expected) in computational biology/chemistry, biochemistry, computer science, biological or chemical engineering, forensic science, or a related field. • Experience in one or more of the following areas demonstrated through at least one first-author publication: computational biology/bioinformatics, cheminformatics, analytical chemistry/mass spectrometry/metabolomics, or machine learning/computer science. • Track record of independence, motivation, and strong written communication skills. • Ability to work with noisy data, data preprocessing, and model evaluation. • Experience with AI/ML for chemical/biological data is desirable.
Term, Location, and Application
Term of appointment is based on rank. Postdoctoral positions are typically one year with potential renewal pending satisfactory performance and continued funding; more senior hires may have multi-year appointments. The work location is in-person on campus at Princeton University and is subject to Princeton University’s background check policy. To apply online, please visit the Princeton academic positions page and submit a CV and cover letter. The cover letter should highlight 1–3 publications or preprints that address the required experience, and include contact information for three references. Qualified candidates who pass an initial screening may be provided with short programming exercises to assess their skills. Only suitable candidates will be contacted.
Compensation and Benefits
Expected Salary Range: $65,000 - $70,000. The University offers a comprehensive benefits program to eligible employees. Please see the University benefits information for more details.
#J-18808-Ljbffr