Data Scientist

Job Summary

OspreyData is developing an IOT analytics platform enabling engineers and operations personnel to collaborate with data scientists building innovative machine learning and artificial intelligence models. The OspreyData platform facilitates the ingestion and transformation of asset, sensor and event data and makes it available in an open source data science environment supporting Python, Jupyter and Spark.

Join our data science team to advance our platform by building predictive and diagnostic models for our oil and gas customers. This is an opportunity for you to work with a passionate team creating a leading edge platform using open source tools to deliver incredible value to customers.


  • Work with customers and industry experts to discover high value use cases for failure detection performance optimization and other actionable insights.
  • Perform exploratory data analysis to discover patterns, trends and performance insights from large, high-dimensional IOT signal data.
  • Profile data sources to assess content, structure, quality and utility.
  • Define analytical experiments to validate hypotheses and test potential solutions using statistical analysis methods on historical data.
  • Incorporate engineering and physics based mathematical models (e.g. fluid dynamics) to enhance and augment sensor signals.
  • Train, test and validate predictive and diagnostic models using machine learning and artificial intelligence algorithms for classification, regression and time-series analysis.
  • Identify and implement new statistical or machine learning methodologies as needed for specific models or analysis.
  • Utilize open source technologies including Python, Jupyter and Spark in combination with the OspreyData platform.
  • Work proactively with software development team to improve the OspreyVision platform.
  • Work with customers and stakeholders to explain and document techniques and results using non-technical language and incorporate feedback.


  • Exceptional understanding and ability to apply quantitative statistical methods and machine learning algorithms to solve complex challenges in business operations and develop predictive and diagnostic models.
  • Master’s Degree in Operations Research, Computer Science, Applied Mathematics, Industrial Engineering, Petroleum Engineering or related field from an accredited college or university.
  • 3+ years experience in data analysis and model development in Python and/or R as well as the ability to implement, maintain, debug and test.
  • Experience using machine learning and artificial intelligence models and packages such as SciKit Learn and TensorFlow.
  • Some experience applying advanced mathematics in one or more of the following fields is a plus:¬†oil and gas, petroleum engineering optimization, simulation, linear programing, integer programming, dynamic programming.
  • Experience in software development is a plus, ideally as part of a team using version control systems such as Git or SVN.
  • Some experience with Spark, Pandas, AWS, MongoDb, OpenTSDB a plus.
  • Ability to work with team members and customers to assess needs and resolve problems using excellent problem-solving skills, verbal/written communication, and the ability to present and explain technical and mathematical concepts to business audiences.
  • Strong attention to detail with the ability to interpret raw data and assess large data sets for data integrity to effectively identify and treat outliers and data anomalies.
  • Passion for learning, evangelizing new technologies and keep up-to-date with latest trends in data science.
  • Willingness to work in a fast paced, entrepreneurial, and technical environment as part of a product and engineering team to build the most innovative and effective product in the market.
  • A positive can-do attitude with a sense of urgency and ability to adjust to changing priorities.


To apply for this position please email a cover letter and resume to