Data Scientist

Description

The company makes a scenario planning and analysis platform that uses AI, and its customers use it to make faster business decisions.

The company serves more than 2,400 companies worldwide, many of them among the Fortune 50.

You would join the Functional Analytics team, which builds analytic engines that plug directly into the company's applications to solve complex enterprise business problems.

The role centres on building ML models and pipelines that produce automated, actionable insights at scale, and on working directly with customers as their technical partner.

Responsibilities

• Lead the technical rollout of the engines for new clients, working with customers, Customer Success, Product and Engineering.
• Hands-on work with client data to adjust ML models so they reflect each client's business logic, operational guardrails and data quirks.
• Design and build scalable analytic capabilities that integrate into the company's applications and turn raw customer data into automated, high-value insights.
• Design, train and deploy machine learning models (LightGBM, XGBoost) and deep learning models (PyTorch) for demand sensing and cold-start forecasting.
• Build and tune scalable pipelines that combine SQL and Python (dbt, Snowflake) to extract localised temporal signals from high-volume retail transaction data.
• Work with engineers to move your models from prototype into monitored, reliable production pipelines using MLflow and Optuna.

Requirements

• Hands-on professional experience in data science, including taking systems from prototype to production in a demanding environment.
• Extensive experience with traditional machine learning, deep learning frameworks and complex time-series forecasting.
• High proficiency in Python and Pandas, with solid software practices: testing, clean code, code review and CI/CD.
• Experience optimising data models and access patterns in modern warehouses such as Snowflake or Databricks, using SQL and transformation tools like dbt.
• Experience with scalable cloud infrastructure on AWS, GCP or Azure, including columnar formats such as Parquet.
• Exposure to MLOps tools for training, tracking, deploying and monitoring models, such as MLflow, Optuna, Prefect or Airflow.
• Desirable: background in supply chain forecasting, enterprise AI or retail analytics.
• Desirable: M.S. or Ph.D. in Computer Science, Artificial Intelligence, Statistics, Data Science or a related quantitative field.

Conditions

The company treats all applicants equally regardless of gender identity or expression, sexual orientation, religion, ethnicity, age, neurodiversity, disability status, citizenship or any other personal characteristic.