Data Scientist
Continuous glucose, the 5th vital sign, now available as part of the Current Health platform. Learn more about our partnership with Dexcom.

Data Scientist

Posted Mar 20 2019

Remote in the UK or US

Full time

Apply for this position

No file selected

Thankyou for your interest in Current. We'll be in touch with you shortly.

What will you do

About the role
We are looking for Data Scientists who are interested in the cross-section between acquisition of physiological signal from the human body and machine learning.

You will work at the intersection between our wearable device and our data platform, Analyse and communicate current performance of algorithms to relevant internal stakeholders. You will create intelligent models to improve real world performance of mathematical based models and time series models to capture new and novel patient deterioration patterns

You will be deeply involved in collating and providing diagnostic information to clinical staff to help them better understand their patients leading to the development of biomarkers for detecting patient disease. You will be expected to assist with the design of human studies to collect data.

You will have the opportunity to work with teams across the whole organisation from Biomedical, Software, Hardware to Sales and Marketing.

About you

  • You will have proven experience with a common data science language (ideally python) and a query language
  • You will have experience manipulating large and deep data sets (from 100s MB to 100s TB)
  • You will have experience with feature extraction and feature selection
  • Experience in presenting data driven decisions to non-technical people
  • Experience in extracting data from multiple sources such as S3, Hive, Athena, HDFS
  • You will have experience with time series modelling
  • You will have strong understanding of how to use statistics to evaluate models
  • You will have proven experience using both labelled and unlabelled data to build models
  • Experience with digital signal processing would be a huge bonus i.e. FFTs, digital filtering, wavelet transforms
  • Familiarity with various data science pipelines and lifecycles for iterating models such as unix/liux pipelines would be ideal
  • Experience with source control preferably Git would be beneficial
  • Familiarity of clinical study protocol design
  • Experience with distributed computing i.e. hadoop, spark, hive would be beneficial
Copy link