Quant Engineer: Data Products (Mid-career / Senior)

Theia Insights; Barcelona; Híbrido; EUR 110.000 - 140.000; Jornada completa

Descripción de la vacante

Theia Insights is seeking a quant engineer for the Data Products team in Barcelona. You will build models behind Thematic Factor Risk Models (TFM) and back-test methodologies, turning research into daily production output with the economics team. This senior group emphasizes correctness and reproducibility.

You will work on statistical modelling, delta risk decomposition, and end-to-end production pipelines, contributing to the data assets that power our financial intelligence products.

Formación

• Experience delivering production-grade Python code.
• Deep understanding of factor risk models and portfolio attribution.
• Strong in statistical modelling with awareness of look-ahead and survivorship bias.
• Familiar with datasets in Pandas and Parquet/Arrow; DuckDB experience is a plus.

Responsabilidades

• Develop statistical models of stock price movements and estimate the performance of thematic trends.
• Construct and back-test factor risk models, decomposing stock returns into thematic and traditional risk factors.
• Design and validate signal-generation and portfolio-attribution methodologies with the economics team.
• Make research reproducible, so published output can be re-run after backfills and restatements.
• Collaborate with pipelines team to move modelling decisions into daily production.

Conocimientos

Python production

Factor risk models

PIT discipline

Statistical modelling

Pandas/Parquet

Herramientas

Statsmodels

cvxpy

PyTorch

DuckDB

Dagster

Airflow

AWS

Descripción del empleo

About The Role

Theia Insights builds foundational financial intelligence products, including industry classification, knowledge graphs and factor risk models, for institutional investors. We serve some of the largest asset managers, hedge funds, index providers and sell-side banks. As a quant engineer on the Data Products team you'll build and run the models behind our Thematic Factor Risk Models (TFM): decomposing stock returns into thematic and traditional risk factors, back-testing methodologies and turning research into daily production output alongside our economics team. The Data Products team owns the data that underpins everything we sell. It's a small, senior group that values correctness and reproducibility over volume, and it sits close to the product leads who shape the methodology.

About The Role

Theia Insights builds foundational financial intelligence products, including industry classification, knowledge graphs and factor risk models, for institutional investors. We serve some of the largest asset managers, hedge funds, index providers and sell-side banks. As a quant engineer on the Data Products team you'll build and run the models behind our Thematic Factor Risk Models (TFM): decomposing stock returns into thematic and traditional risk factors, back-testing methodologies and turning research into daily production output alongside our economics team. The Data Products team owns the data that underpins everything we sell. It's a small, senior group that values correctness and reproducibility over volume, and it sits close to the product leads who shape the methodology.

What You'll Do

• Develop statistical models of stock price movements and estimate the performance of thematic trends
• Construct and back-test factor risk models, decomposing stock returns into thematic and traditional risk factors
• Design and validate signal-generation and portfolio-attribution methodologies in collaboration with the economics team
• Make research reproducible, so that any published output can be re-run exactly, including after backfills and restatements
• Work with the pipelines team to take modelling decisions into daily production

Requirements

Essential

• Strong production Python
• Factor risk models and portfolio attribution in depth: cross-sectional regression, covariance estimation and shrinkage, and back-tests you'd defend line by line
• Point-in-time discipline, look-ahead and survivorship bias, and reconstructing what was knowable on a given date
• Statistical modelling and optimisation (statsmodels, cvxpy; PyTorch useful)
• Datasets in pandas and Parquet/Arrow, plus an analytical engine such as DuckDB

Nice to have

• Quantitative research background, academic or industry
• Index construction and classification taxonomies
• Working with model-derived inputs, understanding that NLP-generated exposures carry measurement error and revise over time
• Task orchestration (Dagster or Airflow) and S3-based data flows
• AWS fluency and CI/CD discipline

Benefits

• Competitive salary plus share options
• 25 working days holiday, plus Spanish public holidays
• Hybrid working from Barcelona