Data Scientist / Software Engineer (Prognostics)

  • Tesla
  • Palo Alto, CA, USA
  • Jun 02, 2021
Full-time Data Security Data Visualization DevOps Kafka Machine Learning MATLAB Python R Software Engineering Spark

Job Description

Data is deeply embedded in the product and engineering culture at Tesla. We rely on data – lots of it – to improve autopilot, to optimize hardware designs, to proactively detect faults, and to optimize load on the electrical grid. We collect data from each of our cars, superchargers, and energy products and use it to make these products better and our customers safer.

We're the Fleet Analytics team, a small but fast-growing central team that helps many teams leverage the data we collect. We help engineers through direct support by doing data analysis for them and through applications and tools so they can self-serve those analyses in the future. To do so, we leverage the internal big data platform that is built on top of Kafka, Spark, Presto and data science tools such as Jupyter notebooks, Pandas, Bokeh, Superset and Airflow.

We're looking for an experienced engineer to join us. This foundational member will provide leadership in the definition and implementation of processes and tools that enable Tesla's data science.

You will lead our Prognostics application, where we build machine learning pipelines to help identify which cars may need service so we can address issues before they inconvenience our customers. Building this application is crucial to improve our customer experience as well as to optimize service operations and logistics. You will own the application end-to-end, from prioritizing which issues to focus on, to building the features and predictive models, to bringing those models to production and writing the code that acts on your predictions. You will directly further our mission by reducing the cost associated with cars breaking down, and strengthening our brand with a customer experience that few companies can achieve.


  • Work with our service organization to prioritize high-value issues
  • Design and build your machine learning pipeline end to end
  • Work with service engineers and firmware engineers to understand what features could help predict issues
  • Build efficient and reproducible data pipelines to produce your features, consuming petabytes of time series data using cutting-edge open source technologies
  • Build machine learning models to predict failures, and anything you need to iterate over your model (feature selection, hyper parameter tuning, validation, etc)
  • Evaluate, justify and communicate model performance
  • Schedule and operate your model in a production data pipeline
  • Build user interfaces to bring humans in the loop when necessary, to further increase the quality of your predictions
  • Write clean and tested code that can be maintained and extended by other software engineers
  • Keep up to date on relevant technologies and frameworks, and propose new ones that the team could leverage
  • Identify trends, invent new ways of looking at data, and get creative in order to drive improvements in both existing and future products
  • Give talks, contribute to open source projects, and advance data science on a global scale


  • Strong proficiency in Python
  • Strong foundation in machine learning
  • Strong foundation in software engineering
  • Experience building multiple machine learning models that provided company value
  • Experience with data science tools such as Pandas, Numpy, R, Matlab, Octave
  • Strong verbal and written communication skills
  • Smart but humble, with a bias for action

Nice to have

  • Experience building, scheduling and operating data pipelines (e.g. using Airflow)
  • Experience building web applications
  • Experience building data visualizations
  • Experience with continuous integration and continuous development
  • Experience in devops, i.e. Linux, Ansible, Docker, Kubernetes
  • Understanding of distributed computing, i.e. how HDFS, Spark, Presto or Kafka work
  • Proficient in Scala

Tesla participates in the E-Verify Program

Tesla is an Equal Opportunity / Affirmative Action employer committed to diversity in the workplace. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, age, national origin, disability, protected veteran status, gender identity or any other factor protected by applicable federal, state or local laws.

Tesla is also committed to working with and providing reasonable accommodations to individuals with disabilities. Please let your recruiter know if you need an accommodation at any point during the interview process.

Job ID