Staff Data Scientist/Machine Learning Engineer

About the Company

Auror is empowering the retail industry to tackle theft and Organised Retail Crime, a $150 Billion problem globally. We connect people and intelligence to reduce crime using technology for good, working with some of the largest retailers in the US, Canada, Australia, New Zealand, and the UK.

Responsibilities

• Design and deploy machine learning models to connect people, vehicles, and incidents across vast datasets
• Detect and map organised retail crime networks using graph analytics and entity resolution
• Build image and video understanding systems for real-time alerts and investigative workflows
• Develop anomaly detection and predictive models to surface emerging threats
• Architect scalable, multi-tenant inference platforms across multiple geographies
• Manage the full ML lifecycle from concept to production, including monitoring and retraining
• Partner with engineers, product managers, and designers to embed ML into the Auror platform
• Contribute to model governance and the Responsible AI Framework

Requirements

• Advanced Python programming and strong SQL skills
• Experience designing, deploying, and monitoring ML models in production
• Ability to communicate complex ML concepts to non-technical stakeholders
• Strong perspective on responsible AI, fairness, and ethics
• Deep expertise in computer vision or LLMs
• Experience with ETL/ELT processes using dbt and Snowflake
• Proficiency with cloud environments (Azure or GCP) and Docker
• Proficiency with Git/GitHub and CI/CD practices
• Experience with the full ML lifecycle including Feature Stores and Model Registries

Preferred Qualifications

• Experience testing production ML models for fairness and bias
• Familiarity with graph or non-relational databases like Neo4j or ElasticSearch
• Experience working with sensitive data across multiple privacy jurisdictions
• Experience with deep learning and NLP libraries such as TensorFlow or PyTorch
• Degree in Statistics, Computer Science, or a related field