Postdoctoral Research Associate - AI/Machine Learning for Mass Spectrometry

Agupdate; Princeton (NJ); On-site; USD 60,000 - 100,000; Full time

Job summary

An innovative research lab at a prestigious university is seeking a Postdoctoral Research Associate to lead machine-learning projects in mass spectrometry-based metabolomics. This role offers the chance to develop cutting-edge computational methods and collaborate with experts in the field. Candidates will engage in exciting research that could impact drug discovery and bioinformatics. If you're passionate about AI and data science, and eager to contribute to groundbreaking work, this position is a fantastic opportunity to advance your career in academia or industry.

Qualifications

• PhD or expected PhD in computational biology or related fields.
• Relevant research experience with at least one first-author publication.

Responsibilities

• Develop machine-learning methods for metabolite identification.
• Collaborate with experimentalists on mass spectrometry data.

Skills

Machine Learning

Bioinformatics

Cheminformatics

Mass Spectrometry

Metabolomics

Education

PhD in Computational Biology

PhD in Chemistry

PhD in Biochemistry

PhD in Computer Science

Tools

Python

R

MATLAB

Job description

Position:

Postdoctoral Research Associate - AI/Machine Learning for Mass Spectrometry

Description:

The Skinnider Lab (https://ludwigcancer.princeton.edu/people/michael-skinnider) at Princeton University seeks to recruit 1-2 postdoctoral or more senior research positions to work on machine-learning projects related to mass spectrometry-based metabolomics data. Positions are available starting July 2024 and will remain open until suitable candidates are found.

Successful candidates will develop and apply computational approaches for mass spectrometry data, focusing on AI/ML. They will lead and contribute to projects such as:

• Developing machine-learning methods for identifying known and unknown metabolites in MS/MS data
• Meta-analysis of mass spectrometry-based metabolomics in human disease
• Re-analysis of large-scale clinical datasets to identify illicit drugs
• Collaborations with anti-doping programs to detect performance-enhancing drugs
• Data curation and development of new resources

Opportunities also exist to develop an independent research agenda aligned with the lab's interests. The work builds on recent publications, including integrating language models with mass spectrometry data (Nature) and developing bioinformatics tools for bacterial natural products (Nature).

The work is computational but involves collaboration with experimentalists. Candidates should be enthusiastic about data preprocessing and curation, as well as model development. This role prepares candidates for careers in academia or industry involving computational biology, cheminformatics, drug discovery, and related fields.

Qualifications include a PhD or expected PhD in computational biology, chemistry, biochemistry, computer science, or related fields, with relevant research experience demonstrated through at least one first-author publication. Candidates should have experience in one or more areas such as bioinformatics, cheminformatics, mass spectrometry, metabolomics, or machine learning.

To apply, visit this link to submit a CV and cover letter, highlighting 1-3 relevant publications, along with contact information for three references. Qualified candidates may be asked to complete programming exercises. The position is in-person at Princeton University and is subject to background checks.