Sr Data Scientist - Global Team - Indaiatuba/sp

John Deere John Deere · Industrial · Indaiatuba, SP, Brazil · Data and Analytics (CA)

Develop, deploy, and monitor predictive models for asset valuation in John Deere Financial. This role involves model lifecycle management, data analysis, SQL query development, and production deployment using MLOps practices.

What you'd actually do

  1. Participate in the development and lifecycle management of the machine learning or regression-based asset value models, this may include development, enhancement, maintenance, and validation of models that are used across a growing number of functions and users within John Deere Financial.
  2. Use a variety of exploratory tools and analytical methods to solve problems by investigating and identifying trends and risks within Asset Valuation. Understand impact to the business and communicate findings to a variety of stakeholders.
  3. Support the development and maintenance of complex SQL queries, dashboards, visualization, and reports in enterprise data platforms such as Databricks, Tableau, Power BI becoming a subject matter expert in asset valuation data sets used by John Deere Financial.
  4. Deploy and integrate analytical models into production using CI/CD pipelines (such as GitHub Actions/Jenkins), adhering to software engineering best practices within the MLOps lifecycle.
  5. Support the development and maintenance of complex SQL queries, dashboards, visualizations, and reports in enterprise data platforms (Databricks, Tableau, Power BI), becoming a subject matter expert in asset valuation datasets.

Skills

Required

  • Bachelor’s, Master’s, or PhD Degree in Finance, Computer Science, Data Analytics, Data Science, Engineering, Math, Statistics, or a related quantitative field
  • Advanced English
  • Python (PySpark), SQL, R or SAS
  • Proficiency across the entire MLOps lifecycle, particularly predictive, machine learning, and time series forecasting
  • Experience to explore and visualize data (with a tool such as Python Dash, R Shiny, Tableau, PowerBI, etc.)
  • Strong experience with standard data science code editors, development environments, and version control tools such as Databricks, VS Code, GitHub, and/or other IDE's

Nice to have

  • Experience connecting to and utilizing a wide variety of on-prem and cloud-based data sources and technologies (e.g. relational databases, data lake environments, etc.)
  • Practical experience collaborating with IT or other Analytics Enablement groups to deploy analytics products to various production environments
  • Knowledge of Agriculture and Construction & Forestry Equipment
  • Knowledge of financial services/products and accounting concepts
  • Experience woriking in data science or a related field

What the JD emphasized

  • Advanced English

Other signals

  • developing, deploying and monitoring the performance of predictive models
  • machine learning or regression-based asset value models
  • Deploy and integrate analytical models into production using CI/CD pipelines (such as GitHub Actions/Jenkins), adhering to software engineering best practices within the MLOps lifecycle.