Senior Data Scientist, Commodity Intelligence - Remote

RELX International; United States; Remote; USD 80,000 - 133,000; Full time

Benefits offered by this job

Pension plan

Public transport benefits

Learning & development

Job summary

ICIS is seeking a Senior Data Scientist to join our Analytics Hubs in Karlsruhe or London. You will build predictive models for commodity markets, create interactive analytics, and collaborate with customers to shape decision-support tools.

You will work with data from global energy, petrochemical and fertilizer markets, applying techniques from statistical modelling to ML, with code in Python and SQL and deployment in our data lakehouse.

Qualifications

• Minimum of 3 to 5 years of practical experience in predictive modelling in the context of (commodity) markets or trading, supply, demand and prices.
• Production-ready code in Python and SQL, using AI-code generation and Spec-Driven-Development.
• Experience with software development practices (modularisation, versioning with Git, tests).
• Familiar with Dash/Plotly and data visualization techniques.

Responsibilities

• Create and continuously improve analytical commodity market models in Python (demand, supply, storage, trade, price forecasting).
• Connect, clean, and impute datasets from diverse internal and external sources.
• Turn raw data into actionable market insights and develop interactive analytics/tools (e.g., Dash).
• Deliver data and models into ICIS Data Lakehouse and shared platforms.
• Discuss models with customers and translate domain knowledge into model improvements.

Skills

Python

SQL

Data visualization

Dash

Tools

Docker

Airflow

Git

Databricks

Snowflake

Job description

ICIS is seeking a Senior Data Scientist to join our Analytics Hubs in Karlsruhe or London. You will build predictive models for commodity markets, create interactive analytics, and collaborate with customers to shape decision-support tools.

You will work with data from global energy, petrochemical and fertilizer markets, applying techniques from statistical modelling to ML, with code in Python and SQL and deployment in our data lakehouse.