Quantitative Analyst I: ML-Driven Alpha & Risk

Develops and maintains global quantitative stock selection models. Develops and improves existing signal evaluations, portfolio construction, and back-tests infrastructure that enhances the investment process. Researches and performs infrastructure development using Python and R. Develops Machine Learning (ML) models by combining data sources. Conducts statistical research to develop new investment products — ESG managed accounts. Transitions existing R code to Python. Updates and enhances social media dashboards and analytics for Equity and High-Income research teams using Tableau. Estimates state sales tax receipts by studying credit card spending data. Primary Responsibilities: Develops new stock selection alpha factors and improves the existing factor library using traditional and alternative datasets. Implements and enhances risk factors and models, and develops risk management tools to mitigate downside risk and exposure. Conducts single path optimization to simultaneously optimize goals and accounts. Develops Smart beta strategies. Back-tests investment disciplines over various phases of the business cycle. Runs optimized pilots for single asset class funds of funds and Multi-Asset Class funds of funds. Runs portfolio stress tests, highlights potential risks as they arise, and suggests remedies to reduce or eliminate unwanted risks. Analyzes and interprets statistical data to identify significant differences in relationships among sources of information. Identifies relationships and trends in data and factors that could affect the results of research. Develops or applies mathematical or statistical theory and methods to collect, organize, interpret, and summarize numerical data to provide usable information. Education and Experience: Master’s degree (or foreign education equivalent) in Accounting, Economics, Finance, Financial Mathematics, Statistics, Mathematics, Financial Engineering, or a closely related field and no experience. Skills and Knowledge: Candidate must also possess: Demonstrated Expertise (“DE”) conducting and streamlining quantitative research on signals and factors using data science techniques — large dataset manipulation, and econometrics/ statistical techniques (macro/micro economic reasoning, multivariate regression, and statistical Machine Learning (ML). DE implementing quantitative strategies and portfolio analytics platforms, using R, Python, Git, subversion, and data science pipelines’ best practices in data extraction, transformation, and computing. DE developing data visualization and analytics dashboards to analyze portfolio characteristics, investment risk and return attributions, risk appetites, and robustness/ sensitivities using PowerBI. DE validating, assessing, and documenting both statistical and qualitative models for capital adequacy stress tests under regulatory requirements; and developing infrastructure and tools to analyze discrepancies in validation and propose remediation plans for model redevelopment, using Python and Excel. Expertise may be gained during graduate degree program. #J-18808-Ljbffr Fidelity Investments Inc.