Bioinformatics Analyst en Boyce Thompson Institute for Plant Research

Description

This position will focus on the development of machine learning techniques and application of those techniques to large-scale biological plant datasets. This will include training and evaluating state-of-the-art machine learning models and developing applications with the models for use by plant genetics researchers. The main area of focus is genetic imputation to assist plant breeders. 

Conduct analyses as directed by a supervisor, including:

o Foundational knowledge in most relevant programming languages, bioinformatic software, and pipeline development tools.

o Design and implement genetic imputation tools for crop species using state-of-the-art machine learning models.

o Train and evaluate various Machine Learning models by curating applicable plant datasets, tuning hyperparameters, developing domain specific loss functions and tracking experiments and results.

o Maintain current knowledge on recent advances in Machine Learning techniques by reading journals and attending seminars/conferences.

o Communicate findings through clear reports and visuals.

o Maintain high code quality through internal peer code reviews, rigorous testing and writing documentation.

o Participation in semi-annual hackathons to assist biologist collaborators’ work on specific projects.

o Operates with complete oversight by the PI, research scientists, and/or specialists in the lab.

Participate in professional development activities, which may include:

o Regular meetings regarding the progress and direction of research with the supervisor or in group meetings.

o Participating in Institute seminars and events.

o Participating in activities to develop communication, management and other soft skills.

o Attending conferences.

Requirements

Education and Certification

· A Master’s degree in Bioinformatics, Computer Science or related fields, or a Bachelor’s degree with significant relevant experience.

Experience and Knowledge

· Experience with Linux

· Proficiency in Python and at least one other programing language such as Perl, Java, Kotlin or R

· Experience with current Machine Learning Algorithms and Techniques and applying them to genomic plant data

· Ability to work effectively in a team environment;

· Good communication and analytical skills.

Communication Skills

Effective written and verbal communication, as well as interpersonal skills, are required. Ability to maintain accurate lab notebooks and electronic records in English. Ability to draft publications and sections of grant proposals. Ability to speak effectively one-on-one or in small groups, and to present information to groups internal and external to the Institute.

Computer Skills

The position requires the proficiency in basic business applications and standard bioinformatics tools. Proficiency with command-line tools required. Proficiency with high-performance computing environments required.