We are a leading multi-strategy hedge fund, is seeking a Quantitative Analyst to join a commodities-focused investment pod in Houston. This is a highly research-oriented role working directly alongside an experienced Portfolio Manager to develop differentiated investment signals using alternative data and quantitative research techniques. The successful candidate will combine a strong foundation in statistics, financial modeling, and Python with a genuine curiosity for uncovering new sources of alpha. Rather than focusing on software engineering, this individual will spend their time researching markets, identifying unique datasets, testing hypotheses, and developing predictive signals that can be incorporated directly into the investment process.
A significant portion of the role will involve sourcing, analyzing, and modeling alternative datasets related to global commodity markets. This includes working with data such as crude oil vessel tracking (AIS), shipping and freight activity, pipeline flows, refinery operations, storage and inventory data, weather, satellite imagery, and other non-traditional datasets. The objective is to transform raw information into robust, statistically validated signals that provide a measurable investment edge.
Responsibilities:- Developing financial time series models and predictive forecasting techniques across energy and commodity markets.
- Researching, evaluating, and incorporating alternative datasets into the investment process.
- Designing, testing, and validating alpha signals through rigorous statistical analysis and backtesting.
- Building research pipelines to clean, organize, and analyze large structured and unstructured datasets.
- Leveraging AI and machine learning techniques to improve feature engineering, accelerate research, and identify differentiated investment opportunities.
- Collaborating with the Portfolio Manager to rapidly prototype new ideas and continuously refine investment models as market dynamics evolve.
Qualifications:- Python and the broader scientific computing ecosystem, including libraries such as Pandas, NumPy, SciPy, and scikit-learn.
- Financial time series analysis, statistical modeling, feature engineering, and hypothesis testing.
- Backtesting frameworks, predictive modeling, and signal evaluation.
- Machine learning techniques and modern AI tools, including large language models, to accelerate quantitative research.
- SQL, cloud-based data platforms, and experience working with large-scale structured and unstructured datasets.
