Data Scientist

• Analyse and improve the performance of a production data matching platform
• Build, test and deploy data-driven improvements to matching logic
• Work across AWS and Kubernetes environments, automating with Bash and Python
• Improve accuracy and reduce false positives to increase operational efficiency
• Partner with engineering teams to take improvements into production
• Support performance testing and ongoing optimisation

We’re looking for a Senior Data Scientist with strong engineering skills to join a major government programme. You’ll work on a large-scale data matching platform that supports national security outcomes, improving its accuracy, performance and reliability in production.

This role suits someone who is as comfortable working in AWS, Kubernetes and the command line as they are analysing data. Direct matching experience isn’t essential. If you’ve worked on classification, deduplication, fraud detection, search or similar problems where precision and recall matter, we’d like to hear from you., * Strong Python (pandas, NumPy, scikit-learn)

• Hands-on AWS experience
• Kubernetes and Docker in a production setting
• Confident with Bash scripting and Linux
• Solid SQL and experience with large datasets
• Good grasp of model evaluation: precision, recall and false-positive tuning

Nice to Have

• Entity resolution, record linkage or fuzzy matching
• Elasticsearch or OpenSearch
• Kafka, PostgreSQL, Jenkins or Ansible
• Government, defence, security, fraud or identity environments, * Analytical Thinking
• Communication Skills
• Data Analysis
• Machine Learning
• Mathematics Knowledge
• Python Programming
• SQL Databases
• Stakeholder Management
• Statistical Knowledge
• TensorFlow & PyTorch Deep Learning