Data Scientist, GHGSat

• Experience: 1-2+ years of experience as a data scientist, with expertise in exploring data and developing machine learning solutions
• Education: MSc or higher in physics, computer science, data science, engineering, theoretical chemistry or biology, mathematics, computational science, or a related field
• Technical proficiency: Confidence writing code (Python, Git) and willingness to learn supporting technologies (e.g. Docker, AWS)
• Core competencies: Knowledge and experience in three or more of the following:
• Exploratory data analysis (e.g. Pandas, NumPy)
• Statistics and machine learning (e.g. Scikit-learn, time-series analysis, Bayesian techniques)
• Mathematical modelling of physical systems (e.g. physics, chemistry, systems biology)
• Deep learning, computer vision and image processing (e.g. PyTorch, Detectron, OpenCV)
• Geospatial modelling (e.g. Rasterio, Xarray, GeoPandas, QGIS)
• Analytical skills. Strong analytical and problem-solving skills with the ability to work collaboratively in a cross-functional team
• Residency requirement. Must be a UK resident with valid work authorization
• Minimum Experience: Mid-level

Desirable

• GHGSat is mapping and tracking the world's greenhouse gas (GHG) emitters. To accomplish this goal GHGSat operates its own satellite and aircraft sensors to collect emissions data, and uses these with third-party data to inform an analytics pipeline that: Detects and quantifies GHG emissions, Identifies and classifies potential GHG emitters and generates valuable insights for our customers
• The successful candidate will extract, analyse, and interpret large amounts of structured and unstructured data from a range of proprietary and public sources, using modern data science techniques to develop emissions intelligence for GHGSat’s analytics products
• Opportunities to contribute to the publication of scientific papers are possible
• Your role will entail: Visualisation and storytelling
• Discovering and evaluating new data sources
• Keeping up to date with relevant scientific literature
• Data preparation for machine learning (e.g. data modelling, automatic data cleaning)
• Develop and cultivate data quality best practices
• Develop algorithms, machine learning models and statistical methods
• Validate, improve, and integrate algorithms and models developed by others
• Operationalise machine learning pipelines on the required infrastructure with the support of engineers
• Present results to technical and non-technical audiences
• Work collaboratively within the Analytics Team and with other subject matter experts to design and prototype solutions for analytics problems
• Demonstrate strong communication skills and critical, bold thinking in all situations
• Build prototypes quickly to address applied scientific and business problems
• Provide high attention to detail with ability to manage and resolve multiple priorities, project complexities and uncertainties
• Keep abreast of latest developments in data science and machine learning