Quant Analyst - Commodities (Oil)

Verition Fund Management LLC (“Verition”) is a multi-strategy, multi-manager hedge fund founded in 2008. Verition focuses on global investment strategies including Global Credit, Global Convertible, Volatility & Capital Structure Arbitrage, Event-Driven Investing, Equity Long/Short & Capital Markets Trading, and Global Quantitative Trading.

We are seeking a quantitative researcher to join a world class commodities trading team. This role is focused on building and enhancing data, analytics, and quantitative tools that support discretionary trading decisions. The ideal candidate combines strong coding and statistical foundations with practical experience applying machine learning and early-stage AI techniques to real-world problems. Prior exposure to crude oil markets is strongly preferred.

Responsibilities:

• Develop and maintain Python-based research, analytics, and data pipelines to support trading and market analysis.
• Design and manage databases and structured data workflows, including SQL-based querying and cloud-hosted data solutions.
• Build dashboards and interactive tools (e.g., Streamlit) to visualize market data, signals, and risk metrics for the trading desk.
• Apply statistical techniques and machine learning methods to analyze historical and real-time market data.
• Contribute to the development and refinement of quantitative signals and core strategies used in commodities trading.
• Explore and implement practical AI applications, including NLP and neural network–based approaches, where relevant to the trading process.
• Work closely with the trader to prioritize projects, translate trading intuition into quantitative frameworks, and iterate quickly.

Qualifications:

• Python (minimum 3+ years of professional experience; required) for data analysis.
• Prior experience in commodities markets, particularly oil, is strongly preferred.
• Git / version control (required).
• Solid applied statistics (e.g., linear and logistic regression, autocorrelation, time-series concepts).
• Machine learning fundamentals and common tools (e.g., SVMs, model evaluation best practices).
• SQL and relational databases (e.g., Snowflake).
• Dashboarding and data visualization (ideally Streamlit).
• Cloud platforms (AWS, Azure, or similar).
• Experience working with large, noisy, real-world datasets.
• Strong conceptual understanding of NLP and neural networks.
• Motivated to build tools and research that directly impact P&L.