Lead Data Scientist — CTV Ad Tech & Data Products

Titan OS Partnership; Bellprat; On-site; EUR 90,000 - 130,000; Full time

Benefits offered by this job

Private health insurance

International work environment

Competitive compensation

Opportunity to shape a fast-growing C2

Job summary

Titan OS is seeking a Lead Data Scientist to turn data into products with a strong focus on advertising: audiences, targeting, measurement and yield. You will write code, ship models, and set the data science direction while mentoring others.

You will work with product, engineering and commercial teams to build data products, design segmentation models, improve ad performance, and define best practices for reproducibility and evaluation.

Qualifications

• 6+ years in data science or ML, with 2+ years leading projects or people.
• Proven track record of data products in production with business impact.
• Experience in advertising or ad tech: audiences, targeting, measurement.
• Strong Python and SQL, knowledge of ML libraries.
• Experience with large datasets and modern data platforms.
• Knowledge of GDPR and data privacy.
• Professional level English.

Responsibilities

• Build data products and production-ready models.
• Design audience segments, scores, APIs or dashboards.
• Collaborate with data engineering for scalable models.
• Lead data science direction with product and engineering.
• Mentor team and set best practices for reproducibility.
• Explain results to both technical and non-technical stakeholders.

Skills

Python

SQL

Machine Learning

Leadership

English

Tools

DBT/SqlMesh

scikit-learn

PyTorch

XGBoost

Job description

Titan OS is seeking a Lead Data Scientist to turn data into products with a strong focus on advertising: audiences, targeting, measurement and yield. You will write code, ship models, and set the data science direction while mentoring others.

You will work with product, engineering and commercial teams to build data products, design segmentation models, improve ad performance, and define best practices for reproducibility and evaluation.