Description
We are currently recruiting for a highly experienced Data Scientist to join a government client of ours5mth contract remote working - Market rates inside IR35
Please note that good knowledge of Pyspark and experience with Pyspark in projects involving big data is essential for the project.
Experience with spatial data would greatly benefit the project.
Scope:
Develop software code for further expanding the use of UN Global Platform AIS shipping data and facilitate its transition from POC to production stage.
Test, maintain, improve, and further development of the current processing pipeline for ingest and processing of AIS data.
Helping with installation, configuration and development of private federated data and synthetic data generation platforms.
Approach:
Apply PySpark and Python for AIS data processing in the UN Global Platform. Understand, maintain and improve the current data processing pipeline for data ingest and ETL.
Develop optimal Docker containers for ingestion and processing of AIS data to run on Kubernetes.
Install, integrate and debug various privacy libraries pySift, OpenDP, Flower.
Improve ML/Deep learning pipelines - pyTorch Automate various infrastructure creation processes, provision infrastructure as code (IaaS) and apply the best cloud security practice in AWS Terraform/ClouldFormation
TYPICAL ROLE RESPONSIBILITIES
Regular reporting to the project team and on-demand to the Senior Leader Team
Deliver well tested and dependable code.
Deliver clear code documentation
- SmartSourcing provides services as an Employment Agency and welcomes applications from all suitably qualified people regardless of age, race, religion, disability, age, gender or sexual orientation.