Director at Quantitative Finance team, Data Analysis and Modelling department

Stack: QuantLib, Optuna, Scipy, PySpark- Developed and calibrated stochastic models for simulating yield curves and foreign exchange rates (GBM, Bates, HJM).- Refactored and enhanced the existing Python library: implemented abstract parent classes, refacrored and optimized code, wrote style guides.

Assistant lecturer for Quantitative Finance (in addition to previous roles)

- Class teacher for Quantitative Finance (2021-...)- Class teacher for Time Series and Panel Data Analysis (2023-...) - Coursework supervisor

Stack: QuantLib, GEKKO, Scipy, PyTorch, CatBoost, HyperOpt, StreamLit, gRPC, Kubernetes- Developed and launched fixed-income portfolio strategies for retail investors, outperforming index-based benchmarks.- Created highly customizable and robust fixed-income optimization library in Python.- Automated anf implemented the pipeline for trading and portfolio rebalancing: position keeping, client requests monitoring,selection of eligible assets, modelling, portfolio optimization, order creation, auto-trading, interactive GUI for monitoring.- Developed the machine-learning algorithm for optimal execution price and volume modelling.- Automated the existing ETFs (index-based or with fixed target weights)

Stack: Statsmodels, Scipy, Scikit-Learn, MinIO (S3)-Consolidated the market risk validation and established it as a separate validation branch:- Increased the number of covered models from 2 to 30.- Validated the wide range of VaR and ALM models: analyzed and retrained them, selected relevant tests, prepared challenger models, wrote reports and recommendations, presented results to owners and stakeholders.- Automated regular model quality monitoring and alerting pipelines.

◦ Analyzed riskiness of the long-short strategies, including ADR and index arbitrages. Computed haircuts and required collateral sizes using statistical models and Monte-Carlo techniques.◦ Created and maintained scripts, internal libraries, manuals. Automated a wide range of tasks including regulatory and internal reports, risk estimation, data collection, and interaction with trading systems.◦ Developed and trained a classifier model to estimate the enhanced VaR of newly-brought securities for the REPO deals.

- Computed the risk-neutral moments (volatility, skewness, kurtosis) for S&P500 options for each day from 2005 to 2020. (Approx. 5500 prices per day, >20m in total)- Calculated a dynamic parameter that predicts a probability of a market crash within the next period. It successfully predicted the 2008 and 2020 crises two weeks before each.- Constructed and back tested an index portfolio using the risk-neutral measures and enhanced Sharpe Ratios, outperforming the static and MVO benchmarks by 30%.

Off-Cycle intern in the Fundamental Equity Research team

Summer intern in the Project Finance (Internal Consulting) team

Summer intern in the Sales and Marketing team