Machine Learning Intern

Key Skills

Bayesian networks, Effective communication skills, Machine learning techniques, Python Programming, R Programming

Job Description

Position: Data Science Predictive Modeling/Machine Learning Intern

Start Date: May 2023 - August 2023

Location: Site Based or Remote

Pivot Bio is developing microbial products that improve the nitrogen sustainability of agriculture by reducing the need for synthetic fertilizers. As a critical member of our Data Science / Computing team, the Data Science Intern will implement supervised machine learning, artificial intelligence, and/or other predictive modeling approaches to extract insights from complex R&D data.

This internship will work within a dynamic and diverse team and be heavily involved in modeling data collected from experimental and commercial fields to identify the environmental and management conditions that lead to maximum product performance. In doing so, you will help us craft the next generation of data-driven research hypotheses and improve our Product Innovation pipeline.

Responsibilities: 

• Build well-documented code and reproducible analytical pipelines to munge, model, and visualize data
• Implement ML/AI techniques to examine experimental and observational datasets
• Note: this is not a ‘big data’ or business analytics role
• Effectively communicate insights to both technical and non-technical collaborators and stakeholders

Physical Demands:

• Job will involve mostly office and computer-based work
• Repeating motions that may include the wrists, hands, or fingers
• Sedentary work that primarily involves sitting/standing
• Communicating with others to exchange information

Qualifications and Experience:

• Currently enrolled PhD or MS student in the Machine Learning space. Domain knowledge of agriculture, biology, ecology or environmental sciences is a big plus
• Proficiency with at least one or more ML/AI modeling framework(s) (e.g., scikit-learn, H2O.ai, PyTorch, Tensorflow, etc.)
• Experience with handling sparse or missing data, small data (p >> n), variable selection, dimensionality reduction, feature engineering and model explainability/interpretability
• Demonstrated ability to build organized, reproducible analytical workflows in Python or R
• Technical background in version control and collaborative coding environments (e.g. Github), and cloud/distributed infrastructure (e.g. AWS) is preferred but not required
• Strong communication and organizational skills

Must be authorized to work in the United States

What we offer: 

• Opportunity to gain professional experience in a progressive company 
• Exciting opportunity to work with a talented and fun team.