AI-powered revenue optimization for transportation, cargo, and live events
Wiremind operates a machine-learning platform for revenue and capacity optimization across airlines, railways, buses, and sports venues. The tech stack is heavily ML-focused—PyTorch, TensorFlow, scikit-learn, XGBoost, LightGBM—paired with data infrastructure (Druid, ClickHouse, PostgreSQL) and orchestration (Argo, Kubernetes). Hiring is concentrated in data roles (7 positions) with a significant intern cohort, signaling rapid model development and engineering momentum. Active projects span 3D cargo optimization, ticket pricing, and demand forecasting—matching documented pain points in capacity planning and demand prediction.
Notable leadership hires: Head of Machine Learning Operations
Wiremind builds AI-driven optimization solutions for high-value, data-intensive industries: passenger transport (railways, buses), air cargo, and live entertainment (sports, events). Founded in 2014 and based in Paris, the company serves industry leaders in France and internationally. Their platform ingests operational data—passenger flows, cargo manifests, ticket demand—and applies machine learning (revenue management, yield optimization, capacity planning) to improve pricing, inventory allocation, and utilization. The product combines predictive models with operational tooling: forecasting engines, pricing engines, and analytics dashboards. Teams handle both model development (improving production performance, reducing data drift) and infrastructure (Kubernetes-based deployment, monitoring via Prometheus and Grafana).
PyTorch, TensorFlow, Keras, scikit-learn, XGBoost, and LightGBM. Supporting tools include MLflow, pandas, NumPy, and Gymnasium for model training and orchestration.
Passenger transportation (railways, buses), air cargo and freight, and sports & events (ticket sales optimization). Clients are industry leaders in France and abroad.
Other companies in the same industry, closest in size