Data Analyst & Programmer - Hur Lab

University of North Dakota • Grand Forks, ND

2d • Onsite

About The Position

We seek a part-time Data Analysts & Programmers to join our collaborative, interdisciplinary team. This role involves developing literature mining pipelines for identifying protein-protein interactions from biomedical texts using advanced language models, enhancing a web-based system for biological gene interaction networks, and creating or integrating natural language processing pipelines for network-based analysis of biomedical entities.

Requirements

• Python programming, Machine Learning, and Natural Language Processing skills.
• Excellent interpersonal and presentation skills, with the ability to interface and communicate effectively with team members from diverse backgrounds.
• Excellent planning, time management, organizational, and work coordination skills.
• Minimum of 3 years of experience in Python programming with a strong understanding of machine learning and natural language processing.
• Demonstrated familiarity with biomedical literature and data mining, as evidenced by at least one research publication, or submissions to conferences, journals, or preprints (to be included as an Appendix in your application).
• Experience in relational database management and web page development, acquired through training courses or research projects. Applicants should include hyperlinks to any developed web page(s) in an appendix, accompanied by several screenshots of these pages.
• A cover letter, a complete CV, and an appendix of publication and web page(s) are required.
• Successful completion of a Criminal History Background Check.
• Must verify identity and eligibility to work in the US and complete the required employment eligibility verification form upon hire.
• This position supports visa sponsorship for continued employment.

Nice To Haves

• Experience in other machine learning approaches.
• Experience in biomedical ontologies.

Responsibilities

• Developing literature mining pipelines for identifying protein-protein interactions from biomedical texts, utilizing state-of-the-art BERT and large language models (LLM), including but not limited to GPT, Claude, Llama2, and Gemini.
• Enhancing Ignet (Integrated Gene Network), a web-based system that leverages centrality and ontology to discover, analyze, and visualize biological gene interaction networks (https://ignet.org).
• Creating or integrating natural language processing pipelines for network-based analysis of biomedical entities.

What This Job Offers

• Job Type: Part-time
• Career Level: Mid Level
• Education Level: No Education Listed