We are seeking a hands-on Data Scientist to take ownership of two machine learning projects at different stages of development and drive delivery within an Azure and Snowflake environment.
This role combines applied data science with practical data and ML engineering. You will need to get up to speed quickly, assess existing work and collaborate with the analytics team to deliver reliable, production-ready solutions.
Key Responsibilities
- Take ownership of two ongoing projects, assessing their current state and establishing clear delivery priorities.
- Review and refine existing models, code and data pipelines.
- Develop and improve model training, evaluation and deployment workflows.
- Support user acceptance testing, investigate source-data nuances and implement necessary enhancements.
- Process and analyse complex datasets, including geospatial, location, labour market and time-series transaction data.
- Optimise geospatial data processing for efficiency and scalability.
- Work with raw and curated data in Snowflake, supporting feature engineering and the use of feature stores.
- Collaborate with analytics and technical stakeholders to validate requirements and resolve delivery issues.
- Maintain version-controlled code, clear documentation and reproducible workflows.
Required Skills and Experience
- Experience delivering data science and machine learning projects into production.
- Strong Python and SQL skills, including data preparation, feature engineering and model evaluation.
- Hands-on experience processing and analysing geospatial data, with an emphasis on performance and efficiency.
- Experience working with time-series and transaction datasets.
- Practical experience with Snowflake and Azure, ideally including Azure Machine Learning.
- Ability to inherit existing projects, assess their current state and make progress with limited handover.
- Familiarity with Git-based source control and collaborative development practices.
- Strong communication skills and a pragmatic, delivery-focused approach.
- Snowflake feature stores and semantic views.
- Azure ML Registry and model lifecycle management.
- Airflow, Astronomer and dbt.
- Terraform and infrastructure-as-code practices.
- Working in environments undergoing data platform consolidation or migration.