Overview
What we are looking for
We are looking for an ambitious research scientist to play a pivotal role in advancing the data strategy we deploy at Jua. Our extensive data warehouse of geospatial data is the secret sauce that enables our models to deliver speed and accuracy for global weather forecasting
As a Senior Data Researcher at Jua, you’ll lead efforts to advance our data capabilities by incorporating cutting-edge techniques like data assimilation and multimodal data fusion. These methods will enable us to seamlessly integrate diverse Earth science datasets into our petabyte-scale warehouse, enhancing the accuracy and richness of our analyses. With your expertise in GIS systems and machine learning, you’ll not only ingest and transform data but also optimize its quality for training our models, driving groundbreaking insights in Earth sciences research.
Responsibilities and tasks
• Working with our Data Engineers to help develop scalable ETL pipelines in the cloud
• Loading… processing, normalizing and providing various data types, from point data such as sensor measurements to raster data such as satellite or radar
• Analyzing and accountability for the resulting quality of new and existing data sets
• Helping to design the architecture and participating in 10x scaling of our data warehouse
• Identifying new novel data sources that bring value to our ML models
• Investigating problems that arise over the e2e pipeline of ingestion through to forecast delivery
• Finding inventive ways to work past known limitations and issues with data sets available within the geospatial community
• Work alongside colleagues within the research group to help benchmark the model against industry standards as well as other models in the market
Need-to-have
• You have at least 5 years of professional experience working in Data Science
• You can showcase deep domain knowledge that is relevant to Jua, such as within Earth Sciences, Meteorology or Remote Sensing
• You have experience with GIS-based data such as satellite, radar, or radiosondes
• You are proficient in Python
• You are proficient with popular Data Engineering libraries such as Zarr, Xarray, and NetCDF
• You are familiar with typical ETL technologies such as Apache Beam or Airflow
• You are familiar with typical ML techniques and how they can applied to solve problems within data science
• You have an intrinsic interest in improving our life on earth with technology
• You have experience in working with petabyte-scale data
• You like to move fast, break things, take risks, think out of the box, iterate and learn fast
• You have experience working in the cloud
Nice-to-have
• You are keen to work closely with Product and our customers to help others understand the value of our data
• M.Sc., and preferably a PhD in computer science, GIS or equivalent experience in data engineering
• You have experience defining and evangelizing data strategy at a company-wide level
• You are familiar with the common machine learning frameworks (PyTorch or FLAX)
• You are familiar with SOTA transformer architectures like GPT, Bart or Swin Transformer
• You have experience working alongside AI research scientists training neural networks
• You have experience working alongside full-stack engineers to take a product to market
Company:
Jua.ai
Qualifications:
Language requirements:
Specific requirements:
Educational level:
Level of experience (years):
Senior (5+ years of experience)
