Computational Associate II - Karczewski Lab

The Broad Institute•Cambridge, MA

23h

About The Position

We are looking for a highly motivated individual to join the Medical and Populations Genetics group at the Broad Institute. This person will be responsible for building, benchmarking, and applying deep learning methods to identify and characterize disease signatures. The candidate should have a very strong computational background and flexibility to learn and apply new skills. The Broad Institute provides a vibrant multidisciplinary research environment with close links to MIT, Harvard and the Harvard-affiliated hospitals across Boston. As a member of our team, you will be provided the opportunity for your contributions to be utilized and recognized across the vast global network of researchers in the fields of genomics and computational biology. The Karczewski Lab is a small lab, and you will work closely with Konrad Karczewski. Candidates must be local to New England and have availability to work part-time.

Requirements

M.S. required in mathematics, computer science, statistics, bioinformatics or other data sciences. Biology graduates with considerable computational experience will also be considered.
Solid understanding of deep learning methods, with experience using at least one of the following frameworks: Pytorch, TensorFlow/Keras, JAX.
Demonstrated attention to detail and analytical skills.
Excellent communication and interpersonal skills.
Excellent written and oral presentation skills.
Strong initiative and ability to take ownership of assigned tasks and projects.
Must be flexible and able to respond to shifting priorities in a dynamic setting.
BS w/ 4+ years of related experience, OR a master’s degree in a related field with 2+ years of related experience.

Nice To Haves

Familiarity with Google Cloud Platform and/or Amazon Web Services, particularly using GPUs, a plus.
Experience with or interest in analyzing large-scale biological data.

Responsibilities

Develop computational infrastructure, including parallelized GPU support.
Build disease models from proteomic data.
Implement deep learning models of genomic data in Pytorch.
Work closely with analyst colleagues to understand and benchmark existing computational methods.
Create pipelines using existing analysis tools to process data in an automated and efficient fashion.
Create reports from data analysis and communicate these to computational staff.