Build and deploy machine learning models to evaluate transactions and customer behaviour in real-time and batch environments

Develop and iterate on fraud detection models through hypothesis-driven experimentation across multiple products

Own the full ML lifecycle from feature engineering and model development through to deployment, monitoring, and continuous improvement

Design and build features from large-scale datasets, including real-time feature generation

Apply advanced modelling techniques (e.g. gradient boosting, deep learning) and take them to production

Collaborate cross-functionally to ship models and ensure they deliver measurable impact

Improve ML infrastructure through pipelines, automation, and internal tooling

Monitor and evolve models to ensure reliability, performance, and robustness over time

Must have experience and skills

Proven track record of building, deploying, and maintaining machine learning models in production, ideally in fraud, payments, or other risk-focused domains

Ability to frame problems, develop hypotheses, and iterate on models through structured experimentation

Strong understanding of the end-to-end ML lifecycle, including monitoring and iteration in production

Experience designing and operating real-time or high throughput data systems (e.g. think Apache Beam, Apache Spark, BigQuery, or similar)

Strong problem-solving skills and ability to operate autonomously in a fast-moving environment

Familiarity with modern ML infrastructure and orchestration tools (e.g. Kubeflow, Airflow, Vertex AI or similar)

Experience with cloud platforms (GCP, AWS, or Azure) and distributed systems

Background in time series data, adversarial modelling, or counterfactual analysis

Experience with deep learning frameworks (e.g. PyTorch)

Contributions to ML tooling, internal platforms, or open-source projects