This position is at McKinsey rapidly identify opportunities for our clients to increase earnings potential and reduce downside risk by back testing various risk management strategies; co-build bespoke tools with client data science teams that tailor machine-learning algorithms to attain an optimal balance of earnings and volatility given clients' risk appetite and capital constraints; and/or collaborate with and train cross-functional client teams to instill long-lasting capabilities and ensure new decision-making models are embraced by organizations.
You will receive best-in-class training in structuring business problems and serving as a client adviser and have opportunities to work closely with and learn from our senior commodity and risk practitioners, as well as industry players that are shaping the future of commodity markets and trading.
You will get access to unparalleled career acceleration, with a huge amount of ownership and responsibility from the get-go in a collaborative, diverse, non-hierarchical environment.
You will get the opportunity to travel to client sites, locally and around the world (once travel resumes).
Lastly, you will be able to provide direct and measurable impact to some of the largest organizations in agribusiness, materials, energy, industrial, and consumer foods sectors around the globe.
As a member of the Commodity Analytics team, you will be based in one of the following offices: Brussels, Amsterdam, Madrid or Lisbon.
You'll work closely with McKinsey's Commodity Trading Service Line to support clients across sectors and geographies.
Commodity Analytics helps commodity producers, processors, buyers, and traders across agriculture/softs, metals,



energy, and consumer sectors improve commodity price risk capabilities with cutting-edge data science.
The Commodity Trading Service Line at McKinsey supports clients in commodity trading and risk strategy, trading operations transformation, and trading and risk digitization driven by deep trading experts with hands-on trading experience and advanced analytics assets.
Our Risk Practice supports clients in many different industries facing challenges of developing and implementing tailored concepts for risk.
Your Background Undergraduate degree is required; Advanced degree in a quantitative discipline (computer science, applied mathematics, economics, quantitative finance, engineering) or equivalent practitioner experience is preferred 2+ years' experience in commodity markets developing market research, trading, or hedging/risk management strategies such as netback/deal economics, signal backtesting, stress testing, and/or hedge effectiveness is preferred but not required 2+ years' experience in physical/cash markets of metals, power/electricity markets, natural gas, crude oil, refined products, and/or ocean freight is preferred but not required 2+ years' experience applying time series analysis of mean-reverting and cointegrated commodity prices/premiums (e.g., ARIMA, VECM,



GARCH),supervised learning (e.g., SVM, LSTM, parallel or sequential tree-based models), unsupervised learning (e.g., PCA, K-means clustering), optimization (e.g., LP/MILP and stochastic models), and/or NLP sentiment analysis is preferred but not required 6+ months' experience with LLM-based analytics in enterprise settings (e.g., document/comms extraction, RAG, evaluation/guardrails) is preferred but not required Experience integrating data science and/or automation workflows with CTRM/ETRM systems via API is preferred but not required Experience automating middle/back-office processes with PRA and LLMs (e.g., pre-trade KYC/credit, trade execution, compliance, logistics, trade settlement) is preferred but not required Production-quality Python for model development, including optimization, time series forecasting, feature engineering, backtesting, and evaluation using standard DS toolkits (e.g., pandas, scikit-learn, statsmodels, gradient boosting, etc.) is required Familiarity with pytest and reproducible research workflow; experience operationalizing models: versioned experiments, CI/CD, model monitoring and drift detection, and collaboration with engineering on APIs and model/solution design is required Experience applying advanced analytical and statistical methods to solve business problems involving commodity markets is required Ability to explain commodity market nuances and/or complex analytics approaches and results in layman's terms to executive audiences across commodity trading, operations, supply chain / logistics, and finance / accounting functions is required --

📌 Senior Data Scientist (Madrid)
🏢 McKinseyEspaña
📍 Madrid