Machine Learning Engineer: Broad Data Sciences Platform
Cambridge, MA

Job Description

Job Description

Machine Learning Engineer: Broad Data Sciences Platform

The life sciences are in the midst of a data revolution. Cheap and accurate genome sequencing is a reality, advanced imaging is routine, and clinical data is increasingly stored in electronic formats. These innovations - and the massive data sets they produce - have brought us to the threshold of a new era in medicine, one where the data sciences hold the potential to propel our understanding and treatment of human disease.

The Broad Institute is committed to accelerating the pace at which the world conquers disease, combining the best of the life sciences and the data sciences. The Institute generates 50 terabytes of sequence data a day and has a history of leading breakthrough research in multiple arenas, from the Human Genome Project to the development of CRISPR (among others).

The Data Sciences Platform (DSP) is the dedicated software engineering group within the Broad institute that works on the Broad's most challenging analysis problems. We are recruiting a new team of Machine Learning Engineers to collaborate with top disease experts and drive new diagnostics, insights, and treatments from massive and proprietary data sets. New developments in machine learning are required to make clinical sense of the multi-modal data that describes disease trajectories.

This cross-collaborative, exploratory undertaking require engineers who are skilled across the entire data pipeline -- from ingest to modeling to validation. We are hiring a team of machine-learning generalists who are fluent in data science stacks and are willing to roll-up their sleeves, identify opportunities across the entire ML stack, and implement scalable engineering solutions.

These are high-profile, high-impact and collaborative roles on a team that can have a transformative impact on the life sciences.

Ideal candidates should be:

* Eager to leverage machine learning to combine different data modalities (time-series, sequence, imaging, and unstructured text data).


* Extremely curious, willing to learn, and collaborate with the top academics and biologists from around the world. Domain expertise in the life sciences is not a requirement.



Qualifications

* Undergraduate degree in Computer Science, or technical field (Physics, Math, etc.)


* 3-5 years designing and training models on large, complex and/or biased datasets.


* 3-5 years experience across deep learning frameworks like Keras, TensorFlow or

PyTorch and machine learning packages (sklearn, etc.)


* Fluent with data modeling, indexing, and ETL and cloud-based pipelines (substantial

expertise with Redshift/BigQuery, Apache Beam, Spark or equivalent)


* Fluent in Python (preferred) or Java



#LI-POST

EOE / Minorities / Females / Protected Veterans / Disabilities

EEO is The Law - click here for more information

Equal Opportunity Employer Minorities/Women/Protected Veterans/Disabled