Millennium's newly formed Risk Informatics group is seeking a Data Scientist to join the team. The individual will be responsible for analyzing and transforming risk data to confirm consistency and correctness as well as produce in-depth risk attribution and decomposition analytics to enhance the firm's ex-ante risk management and ex-post performance evaluation. The individual should possess quantitative knowledge and maturity, deep interest in quantitative risk management, strong technical and programming skills, attention to detail, passion for financial and market data analysis and discovery, be goal oriented and a strong problem solver.
- Develop and implement models to extract time-homogeneous innovations from market data and verify their statistical properties to drive the calculations of ex-ante risk metrics
- Develop and implement multivariate market statistical models to be used for market data outlier detection and quality assurance, mitigation of missing and stale data, risk decomposition and attribution, stress scenario selection, pattern recognition and forecasting
- Develop and implement tools and workflows, in collaboration with Market Risk Technology, for efficient monitoring of risk data quality, exception handling, and data sign-off
- Develop and implement models for Value-at-Risk (VaR) validation, decomposition and interpretation.
- Be an engaged participant in the firm's risk analysis and management
Required Qualifications / Skillsets
- PhD or MS in Financial Engineering, Finance, Statistics, Data Science, Computer Science, Applied Mathematics, Economics or a related field. Alternatively, the candidate can possess a BS in one of the afro-mentioned fields combined with 2 years experience in a quantitative role in the Financial Industry such as a risk quant, risk manager or front office strategist or similar roles
- Deep understanding of statistical model building and verification, inferential statistics and econometrics
- Experience using Data Science tools such as NumPy, pandas, statsmodels, matplotlib, and SciPy in Python
- Experience in Machine Learning principles and tools is highly desirable e.g. scikit-learn, PyTorch, TensorFlow
- Mastery of a programming language and an understanding of good software architecture principles and practices
- Experience processing large data sets on distributed architectures / cloud platforms, for example using Spark or Hadoop, is desirable.