Zürich, Hybrid
3 months
16.8 hours
SL-000948
SL-000948
Job description
- Design, develop, and operationalise advanced time series and anomaly detection models for monitoring abnormal market behaviour in capital markets environments.
- Own the end-to-end lifecycle of analytical models, from business requirement gathering and feature engineering through validation, deployment, monitoring, documentation, and ongoing maintenance.
- Rigorously justify methodological choices based on data characteristics, regulatory context, business objectives, and operational constraints.
- Perform large-scale data analysis using optimized SQL (Oracle) queries and Python-based data pipelines to support model development and investigation workflows.
- Ensure analytical integrity and robustness by proactively identifying and mitigating issues such as spurious correlations, lookahead bias, data leakage, and flawed experimental design.
- Integrate model outputs with external market events and complementary signals (e.g. news or sentiment data) to support event-driven analysis and escalation processes.
- Communicate complex quantitative findings clearly and credibly to cross-functional stakeholders, translating technical results into actionable insights for non-technical audiences.
Requirements
- 7+ years of experience in quantitative data science roles within capital markets, ideally at top-tier banks, asset managers, or fintechs; experience in regulatorily sensitive areas (e.g. market or trade surveillance) is a strong plus.
- Master’s degree or PhD in Quantitative Finance, Mathematics, Physics, Engineering, or a related field, with strong practical application in financial markets.
- Advanced Python expertise for production-grade data science, including OOP, modular design, testing, performance optimisation, and library/package development.
- Deep hands-on experience with pandas, NumPy, SciPy, scikit-learn, statsmodels, and PyTorch or TensorFlow for advanced modelling.
- Extensive experience working with financial time series, including irregular and high-frequency data, microstructure effects, and observational biases.
- Proven track record in building and operationalising time series anomaly detection systems for abnormal market behaviour, with linkage to external market events.
- Strong theoretical and applied knowledge of time series econometrics and anomaly detection, including ARIMA/VAR, GARCH models, change-point detection, and unsupervised learning methods
