Pathology Computational Scientist

Mass General Brigham•Boston, MA

1d•Onsite

About The Position

The Microbiome AI/Deep Learning Lab in the Massachusetts Host-Microbiome Center and Division of Computational Pathology at Brigham and Women’s Hospital/Harvard Medical School is seeking a computational scientist with experience in microbiome bioinformatics and machine learning. You will develop, deploy, and apply microbiome and bioinformatics machine learning approaches, with a special emphasis on deep learning, to a variety of microbiology data sources. Applications will include forecasting microbial population dynamics in the gut, characterizing the impact of spatial structure of the microbiome, predicting impact of the microbiome on host phenotype, tracking infections in human populations, elucidating microbial metabolism, and discovering functions of uncharacterized microbial metabolites and proteins.

Requirements

Must be capable of contributing within an interdisciplinary team, exhibit a high level of initiative, and have an eagerness to learn new technologies.
Ability to manage entire projects in a research environment, from design to implementation, and interpretation of final results.
Must have experience analyzing microbiome data.
Must possess advanced knowledge of machine learning, including model development, training, testing and deploying.
Demonstrated ability to develop and implement computational approaches for analyzing complex biomedical datasets including next generation sequencing data.
Demonstrated ability to manage large and complex biomedical datasets, using tools such as databases.
Excellent written and verbal communication skills with demonstrated ability to communicate complex results to both technical and non-technical audiences, through publications and presentations.
Ability to implement machine learning methods in Python; experience with deep learning and using PyTorch is highly desired.
Knowledge of software engineering best practices, including source code management/control (e.g., Git) and containerization approaches.
Experience with high-performance computing environments, including scheduling systems, e.g., SLURM.
Ability to multitask and prioritize work, to achieve desired goals and deliverables.
Ability to share expertise, coach, and give general direction to others of different skill sets, backgrounds and levels.

Nice To Haves

Experience with deep learning and using PyTorch is highly desired.

Responsibilities

Engage in research developing and applying bioinformatic and machine learning approaches, for a variety of microbiology data sources, including next generation sequencing and metabolomic data.
Substantially contribute to scientific publications and grant applications.
Analyze datasets and produce visualizations and written reports about scientific findings.
Deploy computational pipelines on local workstations and on high performance CPU and GPU clusters.
Organize and curate large datasets using structured approaches, including database systems.
Engage with trainees and other users of the MHMC to facilitate use of computing resources and application of machine learning technologies for the microbiome.
Other duties as assigned.