close banner

Environmental Data Scientist

BreezoMeter is looking for an Environmental Data Scientist with the creativity, professionalism, and passion to be part of the development of innovative data-driven environmental models and insights’ platform, that impacts the lives of millions of users around the world. In this position, you’ll be working with exceptional people in a multidisciplinary R&D team to create inspiring data-driven solutions that you can be proud of.

We Are Looking For People Who Are

  • Curious and enthusiastic to learn new things
  • Independent in their approach and learning
  • Team players
  • Thoughtful, positive, and proactive
  • Flexible and possess a “can-do” attitude
  • Researchers in the heart with strong mathematical intuitions

Responsibilities

  • Data collection, processing, cleaning, and analysis
  • Extending environmental data with third-party sources of information when needed
  • Identifying data and Machine Learning (ML) related opportunities and owning their end-to-end delivery, including research, model development, prototyping, offline validation, implement into production and online testing
  • Leading the ML related roadmap and pushing the domain throughout the entire company
  • Working with fellow engineers and business stakeholders from various disciplines and conveying complex data-related ideas in a concise and clear way
  • Taking an active part in the product ideation process, bringing to the table your deep understanding of data

Requirements

  • Substantial (4+ years) prior experience as a Data Scientist and/or ML Engineer
  • In-depth expertise in machine learning and statistical learning
  • Academic degree in Computer Science, Math, Physics, Electrical Engineering or related disciplines
  • Very strong analytical and problem-solving skills
  • Feeling comfortable with varied types of data and the ability to extract useful insights from it
  • Experience in designing and deploying ML models in large-scale production systems
  • Experience working with time-series data and forecasting models
  • Proficiently with SQL and various types of data stores
  • Excellent familiarity with Python
  • Extensive experience with data science tools (Jupyter Notebook, Pandas, scikit-learn etc.)
  • Familiarity with distributed computing techniques and frameworks (e.g. Apache Spark)
  • Top-notch communication skills, ability to formulate and articulate the problem in hand, approaches to solutions, and results

Bonus Points

  • Familiarity with health-related data sources and prior experience working on health insights systems - big advantage!
  • Scientific background and/or practical experience in the air pollution sciences - big advantage!
  • Familiarity with environmental data sources and related ML models
  • Experience working with data pipelines and various data store types
  • Familiarity with one of the leading public cloud platforms (preferably Google Cloud Platform)
  • Familiarity with software development and design principles
  • Familiarity with modern ML lifecycle management frameworks (e.g. MLFlow)
  • Experience in Deep Learning, with hands-on work with Keras/TensorFlow/PyTorch
  • Familiarity with Geographical Information Systems (GIS)