Data Engineer

About the Role

We are looking for a Data Scientist & Data Engineer who can transform complex mobility, vehicle, and sensor data into reliable, scalable, and business-relevant analytical products. This position combines data science, data engineering, geospatial analytics, machine learning, and stakeholder collaboration to support the development of innovative mobility solutions.

You will work with large-scale datasets originating from connected vehicles, sensors, and external data sources, helping to design analytical solutions that improve understanding of road conditions, vehicle behaviour, and mobility patterns.

Key Responsibilities

• Explore, clean, combine, and transform complex datasets from connected systems, sensors, and external sources.
• Design and maintain analytical workflows for mobility, road-condition, and vehicle-behaviour use cases.
• Perform geospatial analysis, including map matching, spatial quality checks, coverage calculations, and trajectory processing.
• Develop, validate, and improve statistical and machine learning models using supervised and unsupervised techniques.
• Define data validation strategies and investigate anomalies, bias, inconsistencies, and coverage gaps.
• Convert prototypes and proof-of-concepts into robust, maintainable, and production-ready data pipelines.
• Operate and optimize cloud-based data workflows with a strong focus on automation, monitoring, and traceability.
• Deliver analytical reports, dashboards, maps, and visualizations that support informed business decisions.
• Collaborate with engineers, data providers, business stakeholders, and external partners to ensure data quality and alignment on requirements.
• Participate in Agile ceremonies, technical reviews, documentation, and knowledge-sharing initiatives.

Required Skills & Experience

Technical Skills

• Strong experience with Python and data analytics libraries such as pandas, NumPy, and scikit-learn.
• Solid understanding of data engineering concepts, including ETL/ELT processes, schema management, automated pipelines, and data quality controls.
• Experience with SQL, Git, and collaborative software development practices.
• Knowledge of geospatial analytics using tools such as GeoPandas or similar technologies.
• Familiarity with cloud platforms, scalable compute environments, and container technologies. Experience with AWS and Docker is highly valued.
• Experience building and validating machine learning models, including feature engineering, model evaluation, and uncertainty analysis.
• Strong reporting and data visualization skills, with the ability to communicate findings effectively to non-technical audiences.

Nice-to-Have Experience

Experience in one or more of the following areas will be considered a strong advantage:

• Connected vehicles, IoT, telemetry, transportation, infrastructure, or other sensor-driven environments.
• Time-series analytics, computer vision, deep learning, or generative AI.
• Digital twin technologies.
• Taking proof-of-concepts through to production-grade data products.
• Scientific research, experimental design, or regulated environments.
• Validation of algorithmic outputs using reference datasets or human-reviewed ground truth.

Languages

• Professional proficiency in English
• Good command of French

What We're Looking For

The ideal candidate combines strong analytical skills with a pragmatic engineering mindset. You are able to work independently, navigate ambiguity, and translate complex technical findings into actionable insights. At the same time, you thrive in collaborative environments and enjoy working closely with experts from multiple disciplines.

Key Competencies

• Analytical rigor
• Ownership and accountability
• Pragmatism and solution orientation
• Clear communication
• Collaboration and teamwork
• Adaptability in evolving environments