Senior Data Scientist

Softlanding; Porto; Híbrido; EUR 60.000 - 90.000; Jornada completa

Descripción de la vacante

Softlanding seeks a senior data scientist to lead end-to-end data science projects in Porto, delivering production-ready ML models and robust evaluation frameworks. You will collaborate with product managers and engineers to translate business challenges into measurable analytics solutions, ensure model monitoring, drift analysis, and responsible AI practices.

The role emphasizes strong Python/SQL skills, distributed processing, and experience with Databricks/Snowflake/Azure ML in a modern data

Formación

• Strong ML/statistical modelling expertise.
• Proficiency in Python and SQL for data analysis and production-grade solutions.
• Experience with distributed data processing frameworks like Spark.

Responsabilidades

• Lead end-to-end data science lifecycle from problem definition to deployment and monitoring.
• Partner with Product Managers to define success metrics and translate business challenges into analytics solutions.
• Develop, validate, and deploy models for use cases such as fraud, credit risk, pricing, churn and mobility services.

Conocimientos

Advanced ML

Statistical modelling

Python

SQL

Spark

Git workflows

Production ML

Model evaluation

NLP

Experiment design

A/B testing

Herramientas

Databricks

Snowflake

Azure ML

Descripción del empleo

You’ll have the opportunity to collaborate with a leading European mobility services provider, headquartered in Germany and backed by nearly 90 years of expertise. As part of this journey, you’ll contribute to the launch of a new Tech Hub in Porto, helping to drive innovative, technology-led solutions that are transforming how businesses move while contributing to a more sustainable future.

YOUR ROLE

• Lead the end-to-end data science lifecycle, from problem definition and data preparation to model deployment, performance monitoring, and continuous improvement.
• Partner with Product Managers and business stakeholders to define success metrics, evaluate data sources, and translate business challenges into measurable analytical solutions.
• Develop, validate, and deploy statistical and machine learning models for use cases such as fraud, credit risk, pricing, churn, and mobility services, applying robust validation, experimentation, and A/B testing methodologies.
• Collaborate with Analytics Engineers, Data Engineers, and ML Engineers to define features, data-quality requirements, and scalable AI and analytics solutions.
• Deliver production-ready models, including monitoring, retraining criteria, drift analysis, and evaluation frameworks for LLM-based solutions.
• Apply best practices in model validation, explainability, bias assessment, Responsible AI, governance, and regulatory compliance.
• Communicate methods, assumptions, uncertainty, trade-offs, and recommendations clearly to technical and non-technical stakeholders.
• Contribute to data science standards, reusable frameworks, code reviews, and mentoring initiatives.
• Strong knowledge of statistics, probability, experimental design, power analysis, model validation, and machine learning.
• Experience working in cross-functional environments with strong stakeholder engagement.
• Experience with causal inference, fintech, payments, fraud, credit risk, pricing, mobility services, model risk management, or AI regulatory frameworks (nice to have).

YOUR PROFILE

• Strong expertise in advanced machine learning and statistical modelling techniques, including gradient boosting, classical ML, and time-series forecasting.
• Proficiency in Python and SQL for data analysis, modelling, and production-grade solutions.
• Hands-on experience with Spark and other distributed data processing frameworks in large-scale environments.
• Solid understanding of Git-based development practices, version control, and reproducible ML workflows.
• Proven track record of deploying, monitoring, and maintaining machine learning models in production alongside engineering teams.
• Strong knowledge of model evaluation, performance monitoring, drift detection, error analysis, and retraining strategies.
• Familiarity with Databricks, Snowflake, and Azure Machine Learning (nice to have).
• Exposure to NLP, deep learning, and evaluation frameworks for LLM-based solutions (nice to have).
• Knowledge of causal inference techniques and advanced experimentation methodologies (nice to have).
• Active involvement in open-source initiatives, technical communities, or data science knowledge-sharing activities (nice to have).
• Experimental design, A/B testing, control groups, power analysis and quasi-experimental methods.
• Strong English (international working environment).