About the role
You will build machine learning models, from fraud detection to forecasting, and take them from experiment to reliable production. You will own the full lifecycle: data, training, deployment and monitoring.
What you will do
- Build, train and evaluate machine learning models
- Work on fraud and anomaly detection and forecasting
- Build training and data pipelines
- Deploy models and monitor drift and performance (MLOps)
- Track experiments and models with MLflow or similar
- Explain results clearly to technical and business teams
Minimum qualifications
- Bachelor's or Master's degree in Computer Science, Mathematics, Statistics or a related field
- 5+ years in machine learning, including models in production
- Production Python with PyTorch or scikit-learn
- Models you deployed with monitoring (show code or a case study)
- MLOps with MLflow, Docker and CI/CD
- Strong statistics, shown in your past work
- English at CEFR C1 or above (IELTS 7.0 or equivalent)
Expert knowledge
- Model evaluation: imbalanced data, precision-recall trade-offs and calibration
- Feature engineering and data leakage prevention
- Production monitoring: data drift, concept drift and retraining triggers
- Anomaly and fraud detection methods for streaming data
Preferred qualifications
- Master's or PhD in a quantitative field
- Fraud or anomaly detection in production
- Kaggle results, papers or open-source ML work
- AWS ML Specialty or Google Professional ML Engineer
Before any offer we verify your certificates, qualifications, references and right to work in the UK. Security roles also need background screening (BPSS) and may need security clearance.
SOWTK is an equal opportunity employer. We welcome applicants of every background and do not discriminate on any characteristic protected by the Equality Act 2010.