> Markdown version of [/jobs/ext/4023759-lead-data-scientist-titan-os-hybrid](https://www.wearedevelopers.com/jobs/ext/4023759-lead-data-scientist-titan-os-hybrid). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Lead Data Scientist - Titan OS (Hybrid)

- **Company:** Latam. Titan Os
- **Location:** Barcelona, Spain
- **Contract:** Permanent contract
- **Skills:** A/B Testing, Application Programming Interfaces (APIs), Big Data, Software Quality, Information Engineering, Data Infrastructure, Python (Programming Language), Machine Learning, Automation of Marketing, Recommender Systems, SQL Databases, Data Streaming, Feature Store, Pytorch, Model Validation, Yield Optimization, Scikit Learn, Xgboost, Machine Learning Operations
- **Published:** October 30, 2026
- **Apply:** https://www.adzuna.es/details/5945773588

## About the Role

* 6+ years of experience in data science or machine learning, with at least 2 years leading projects or people, including hiring.
 * A track record of building data products that went to production and had a clear business impact.
 * Experience in advertising or ad tech: audiences, targeting, measurement, programmatic or similar.
 * Strong skills in Python and SQL (DBT/SqlMesh), and good knowledge of the usual ML libraries (for example scikit-learn, PyTorch, XGBoost).
 * Solid statistics: experiment design, causal inference, forecasting.
 * Experience working with large datasets and modern data platforms .
 * Good understanding of data privacy and how it affects modeling (consent, GDPR).
 * Professional level of English.

Nice to have

 * Experience in CTV, streaming, media or TV measurement.
 * Knowledge of identity graphs, household matching or data clean rooms.
 * Experience with recommender systems.
 * Experience with MLOps tools (feature stores, model registries, orchestration).
 * Knowledge of the IAB standards (TCF, OpenRTB).

## Description

We are looking for a Lead Data Scientist to turn our data into products. You will build models and data products that create real value for the business, with a strong focus on advertising: audiences, targeting, measurement and yield.

Advertising will be your main area, but not the only one. You will also help other teams with content recommendations, user engagement and business analytics.

This is a hands-on lead role. You will write code and ship models yourself, and you will also set the direction for data science at Titan OS, mentor other people and work closely with product, engineering and commercial teams.

What you will do:Build data products

 * Take ideas from the first question to a product in production: define the problem, build the model, measure the impact and improve it.
 * Design data products that other teams and partners can use, for example audience segments, scores, APIs or dashboards.
 * Work with data engineering to make sure models run reliably at scale, with good monitoring and clear ownership.
 * Decide when a simple solution is good enough and when a more complex model is worth it.

 * Build audience and segmentation models based on viewing behaviour, content and device data.
 * Develop targeting, lookalike and contextual models for CTV campaigns.
 * Improve ad performance and revenue: forecasting of inventory, pricing and yield optimization, frequency and reach.
 * Design measurement and attribution methods so advertisers can understand the value of their campaigns.
 * Work with identity and enrichment data (household and device level) to improve reach and match rates.

Other areas

 * Content recommendations and personalization for the home screen and FAST channels.
 * User engagement and retention analysis.
 * Support business decisions with clear analysis, experiments and A/B tests.

Leadership

 * Set the data science vision and roadmap together with product and engineering.
 * Build the data science team from scratch: hire, mentor and grow new data scientists.
 * Define good practices: code quality, reproducibility, experiment design and model evaluation.
 * Explain complex results in a simple way to technical and non-technical people, including clients and partners.