Job description

Location
Phoenix, Arizona
Status
Open

Description

We are seeking a Data Scientist within Nikola’s Propulsion Engineering team, who will manage & implement advanced analytics projects – with responsibilities ranging from research, analysis, design, building, scale-up, optimization, and validation of cutting-edge algorithms to support data modelling & analytics objectives. You will be performing statistical modelling, develop algorithms and ML based predictive applications to extract deep insight towards continually improving propulsion product quality & performance, not limited to data science applications of component degradation, fault diagnosis, engineering root-cause analysis, etc. In this role, you will have strong cross-functional collaboration with hardware component owners, system architects, vehicle feature owners and simulation/control engineers. You will also provide inputs to the design of prognostic solutions for telemetry data.

You Have:
  • Years of experience: 3+
  • Strong understanding of statistical methods, data structures, strategies to improve overall hygiene/quality of data, transformation/aggregation techniques, feature engineering and multivariate data analysis
  • Strong working knowledge of supervised and un-supervised learning algorithms/methods, but not limited to clustering, classification, regression, dimensionality reduction, anomaly detection, causal inference, neural networks (preferably with prior experience in time-series data modelling)
  • Strong working knowledge of machine learning algorithms, optimize performance, calibrate hyperparameters, assess accuracy and develop validation techniques
  • Fluency in SQL queries, and Python in a distributed database framework – such as HDFS, Spark/Presto, etc. (preferably working with large time-series datasets)
  • Good experience with ML tools, pipelines and libraries – scikit-learn, pySpark, TensorFlow, Keras, Dask, tsfresh, Flint, Darts, PyFlux, etc. (time-series focused)
  • Prior experience in building ML applications for time-series big-data in a relevant domain
  • Good working knowledge with SQL relational databases / No SQL databases
  • Proficiency in data mining/exploratory data analysis, and perform data processing/cleaning/transformation as necessary in preparation steps for model/algorithm development
  • Good working knowledge in building exploratory data analysis (EDA) API/tools for visualizing and monitoring the analytics from time-series database systems. For example: Grafana, or similar
  • Demonstrable experience with big data ‘time-series’ data pipelines and be able to work with unstructured data from different sources, for modelling & analysis
  • Proficient in building visualization dashboards using Power BI, Plotly, Dash, or similar
  • Proficiency with version controlling system - GIT/SVN, and working knowledge of project management tools JIRA/JAMA
Preferred Experience:
  • 5 years of experience in a similar role
  • Working knowledge with cloud-platforms (AWS, Azure, etc) and related services
  • Knowledgeable about telematic data services in trucks, fleet management, other related domains is a plus
  • Familiarity of electrified propulsion systems, physical vehicle test data, CAN-based data loggers and supporting analysis of the test data is a big plus
  • Basic knowledge of control systems
Candidates must have current U.S. work authorization or be TN eligible from Mexico or Canada. This position is not eligible for CPT or OPT.
#LI-RM1

Please let the company know that you found this position on this Job Board as a way to support us, so we can keep posting cool jobs.