Data Scientist

We are looking for a Data Scientist with 5+ years of work/industry experience developing ML models. In addition, you should have at least two years of industry experience developing production-grade ML models for predictive / prognostics and condition-based maintenance.

Glassbeam is a VC-funded startup with a positive work environment. You will have opportunities to work on challenging problems and make an impact. We empower you to take ownership and try new ideas.

Get a sense of accomplishment from building innovative products. Play an important role in the success of our customers and Glassbeam.

Responsibilities

Build predictive maintenance / prognostics products for different types of medical devices. A few examples of the problems that you will be solving:

• Reduce unplanned downtime for medical devices

• Reduce mean time between medical device failures

• Improve patient safety

• Increase device utilization and efficiency

You will own the complete end-to-end ML workflow:

• Develop domain expertise and in-depth understanding of different types of medical devices

• Formulate a business problem into a ML problem

• Conduct EDA on messy unstructured operational (non-patient) data from medical devices

• Determine the right ML techniques that can applied on the available datasets

• ETL, cleanse and prepare data for ML

• Train ML models

• Collaborate with others to deploy, monitor, and manage ML models in production

Requirements

The ideal candidate is an experienced Data Scientist highly skilled in:

• Training, deploying, and managing the complete lifecycle of ML models for predictive maintenance / prognostics and condition-based maintenance

• Framing business problems into ML/data science problems

• Analyzing and preparing complex messy unstructured data for ML

Minimum (must-have)

• 5+ years' work / industry experience as a Data Scientist developing production-grade ML models

• 2+ years' work experience developing production-grade ML models for predictive maintenance

• 1+ years' industry experience training ML models for condition-based maintenance

• In-depth knowledge of different ML algorithms, frameworks, libraries, and related tools

• Excellent exploratory data analysis, data cleansing, data prep and feature engineering skills

• Strong knowledge of statistics

• 2+ years' work experience using R / Python / Scala and SQL

• Hands-on experience working with big data technologies such as Spark and HDFS

• Master’s or Ph.D. in Math, Statistics, Computer Science, or another quantitative field

Plus (not a must-have but desirable)

• MLFlow, KubeFlow

• Spark Mllib

• Scala

• HDFS, Cassandra, Vertica, Delta Lake

• Tableau, Superset