Team Lead Data Scientist

ABOUT THE OPPORTUNITY

Join a leading gaming and entertainment technology company as a Team Lead Data Scientist and drive machine learning initiatives that power data-driven decision making, automation, and personalized customer experiences across a global platform. 

You'll be working for a technology-driven organization where data science and machine learning are core to the business strategy, enabling automated services while delivering tailored customer experiences at scale. The machine learning team builds diverse models ranging from binary classification tasks to sophisticated recommendation systems, transforming business needs into production applications across various business sectors utilizing different data types and handling broad project diversity.

As Team Lead, you'll combine strong technical expertise in machine learning with leadership responsibilities, guiding data scientists through the full model development lifecycle while ensuring delivery of high-quality production systems. Your team comprises data scientists, machine learning engineers, and data engineers, providing the complete skillset to deliver end-to-end projects from experimentation through production deployment and monitoring.

Critical Requirements: This is a lead-level position requiring background in Computer Science, Statistics, Math or related field with strong knowledge of machine learning algorithms and 2-8 years hands-on experience delivering ML models to production. MANDATORY expertise in Python machine learning ecosystem, Spark (PySpark), solid OOP software background, team leadership experience, and strong skills in teamwork, communication, and analytical thinking. English fluency (B2+) essential for team leadership and stakeholder communication.

PROJECT & CONTEXT

You'll be leading machine learning initiatives for a global gaming and entertainment platform where data-driven decisions enable service automation and personalized customer experiences at massive scale. The company's aim is leveraging machine learning across diverse business sectors to optimize operations, enhance user engagement, and deliver value through intelligent automation and recommendation systems that serve millions of active users.

Your team leadership responsibilities center on guiding data scientists through the complete model development process, from translating business requirements into machine learning problems through production deployment and monitoring. You'll mentor team members on best practices, facilitate knowledge sharing, coordinate with machine learning engineers and data engineers for production implementation, and ensure the team delivers high-quality models that solve real business challenges effectively.

Translating business requirements into machine learning problems is a core competency - you'll work with stakeholders to understand business objectives, identify appropriate ML approaches, define success metrics, and design experiments that validate model effectiveness. Your ability to bridge business needs and technical solutions ensures the team focuses on high-impact projects that deliver measurable business value.

Exploratory Data Analysis (EDA) and feature engineering form the foundation of model development - you'll guide the team in understanding data distributions, identifying patterns and relationships, handling missing data and outliers, and engineering features that capture business logic and improve model performance. Your analytical thinking and experimental design skills ensure thorough data understanding before model training begins.

Comparative experiments for model training require rigorous methodology - you'll implement best practices for model selection comparing different algorithms and architectures, parameter tuning using systematic approaches like grid search or Bayesian optimization, cross-validation strategies that ensure robust performance estimates, and evaluation metrics appropriate for business objectives. Understanding ML algorithm theory enables informed decisions about model architecture and training approaches.

The Python machine learning ecosystem is your primary toolset - you'll leverage libraries including scikit-learn for classical ML algorithms, pandas for data manipulation, NumPy for numerical computing, and visualization tools for analysis and communication. Your deep knowledge of Python ML tools enables efficient model development and experimentation.

Spark (PySpark) expertise is essential for processing large-scale data - you'll design and implement distributed data processing pipelines, train models on massive datasets using Spark MLlib or integrating with other ML frameworks, optimize Spark jobs for performance and resource efficiency, and handle the unique challenges of distributed machine learning. Understanding Spark architecture and PySpark programming patterns enables scalable ML solutions.

Your solid software background in Object-Oriented Programming ensures models are built with engineering discipline - you'll structure code for maintainability and reusability, implement design patterns appropriate for ML workflows, write testable code with proper abstractions, and follow software engineering best practices that enable production deployment. Understanding OOP principles distinguishes production ML engineering from experimental notebook work.

Production model delivery is the ultimate goal - your 2-8 years of hands-on experience delivering machine learning models to production means you understand the full lifecycle beyond experimentation including model serialization and versioning, integration with production systems and APIs, monitoring model performance and data drift, implementing retraining pipelines, and maintaining model reliability at scale.

Working on diverse project types keeps the work engaging - you'll tackle binary classification for predictive tasks, multi-class classification for categorization, regression for continuous predictions, recommendation systems for personalized content and product suggestions, and potentially other ML domains. The broad project diversity across business sectors provides opportunities to apply different techniques and learn continuously.

Strong teamwork, communication, and analytical thinking define your leadership approach - you'll communicate technical concepts to business stakeholders, collaborate across data scientists, ML engineers, and data engineers, facilitate knowledge sharing and technical discussions, provide mentorship and career development support, and foster a culture of experimentation, learning, and engineering excellence.

Core Tech Stack: Python (scikit-learn, pandas, NumPy), PySpark (Spark MLlib), machine learning algorithms, statistical analysis

ML Focus: Supervised learning (classification, regression), recommendation systems, feature engineering, model optimization, production deployment

Infrastructure: Distributed computing with Spark, cloud platforms, production ML systems

Leadership: Team guidance, mentorship, stakeholder collaboration, project coordination, best practice establishment

Domain: Gaming and entertainment technology, customer personalization, automation, user engagement optimization

Scale: Global platform serving millions of users, large-scale data processing, high-impact business applications

WHAT WE'RE LOOKING FOR (Required)

Educational Background: Background in Computer Science, Statistics, Mathematics, or related technical field providing foundation in computational thinking and mathematical rigor - this establishes the core knowledge base

Machine Learning Knowledge: Strong knowledge of machine learning algorithms and respective theory including supervised learning (linear models, tree-based methods, ensemble techniques), unsupervised learning (clustering, dimensionality reduction), model evaluation methodologies, and understanding of algorithm strengths, weaknesses, and appropriate applications

Production ML Experience: MANDATORY - 2-8 years of hands-on experience delivering machine learning models to production environments, understanding the full lifecycle from experimentation through deployment, monitoring, and maintenance

Python ML Ecosystem: MANDATORY - Deep knowledge of Python machine learning ecosystem including scikit-learn, pandas, NumPy, matplotlib/seaborn, Jupyter notebooks, and understanding of Python best practices for data science

PySpark Expertise: MANDATORY - Hands-on experience with Spark and specifically PySpark for distributed data processing, understanding Spark architecture, DataFrames API, and building scalable data pipelines for ML

Object-Oriented Programming: MANDATORY - Solid software background in OOP including understanding of classes, inheritance, polymorphism, design patterns, and ability to structure code for maintainability and production deployment

Team Leadership: MANDATORY - Experience leading teams or mentoring data scientists, coordinating project work, providing technical guidance, and driving team success through collaboration

Business Translation: Ability to translate business requirements into well-defined machine learning problems, understanding stakeholder needs and framing appropriate technical approaches

EDA Proficiency: Strong skills in exploratory data analysis including statistical analysis, data visualization, hypothesis testing, and deriving insights from complex datasets

Feature Engineering: Expertise in feature engineering techniques including feature creation, transformation, selection, and encoding strategies that improve model performance

Experimental Design: Understanding of experimental design principles for model training including comparative experiments, A/B testing concepts, and rigorous evaluation methodologies

Model Selection: Implementation of best practices for model selection including algorithm comparison, hyperparameter tuning, cross-validation, and systematic evaluation

Analytical Thinking: MANDATORY - Strong analytical thinking abilities for decomposing problems, identifying patterns, reasoning about data and models, and making data-driven decisions

Teamwork Skills: MANDATORY - Strong teamwork skills for collaborating with data scientists, ML engineers, data engineers, and cross-functional stakeholders

Communication Excellence: MANDATORY - Excellent communication abilities for explaining technical concepts to diverse audiences, documenting work, and facilitating team discussions

English Fluency: MANDATORY - Fluency in English both oral and written for team leadership, stakeholder communication, technical documentation, and international collaboration (B2+ level minimum)

Work Authorization: Eligibility to work remotely from Portugal with availability for full remote collaboration

NICE TO HAVE (Preferred)

Azure Cloud Platform: Experience with Microsoft Azure cloud services for ML workflows including compute, storage, and deployment capabilities

Databricks: Hands-on experience with Databricks unified analytics platform for collaborative data science, MLflow for experiment tracking, and Delta Lake for data management

Deep Learning: Knowledge of deep learning architectures, frameworks (TensorFlow, PyTorch, Keras), neural network training, and applications of deep learning to business problems

Recommendation Systems: Specific experience building recommendation systems including collaborative filtering, content-based filtering, hybrid approaches, and recommendation evaluation metrics

MLOps Practices: Experience with MLOps practices including model versioning, CI/CD for ML, automated retraining, model monitoring, and production ML infrastructure

Cloud ML Services: Familiarity with cloud ML services like Azure Machine Learning, Azure Databricks, or AWS SageMaker for managed ML workflows

Advanced ML Techniques: Knowledge of advanced techniques like gradient boosting (XGBoost, LightGBM, CatBoost), stacking/blending, AutoML, or neural architecture search

Natural Language Processing: Experience with NLP techniques for text classification, sentiment analysis, named entity recognition, or text generation

Computer Vision: Knowledge of computer vision techniques for image classification, object detection, or image segmentation

Time Series Analysis: Experience with time series forecasting, anomaly detection, or sequential data modeling

Reinforcement Learning: Understanding of reinforcement learning concepts and applications

Bayesian Methods: Knowledge of Bayesian approaches to machine learning including probabilistic models and uncertainty quantification

Causal Inference: Understanding of causal inference methods and experimental design for measuring treatment effects

Feature Stores: Experience with feature store technologies for managing and serving ML features

Model Serving: Hands-on experience with model serving frameworks and technologies for production inference

A/B Testing: Deep experience designing and analyzing A/B tests for ML models and product features

Big Data Technologies: Experience with additional big data tools like Hadoop, Hive, Kafka, or cloud data warehouses

SQL Proficiency: Strong SQL skills for data extraction, transformation, and analysis

Data Visualization: Advanced data visualization skills using tools like Tableau, Power BI, or Plotly for stakeholder communication

Git Version Control: Proficiency with Git for code versioning and collaboration on ML projects

Docker & Kubernetes: Understanding of containerization and orchestration for deploying ML models

Gaming Industry: Previous experience in gaming, entertainment, or related industries with understanding of user engagement and personalization

Agile Methodologies: Experience working in Agile teams with sprints and iterative delivery for ML projects

Statistical Testing: Deep knowledge of statistical hypothesis testing, confidence intervals, and significance testing

Optimization Algorithms: Understanding of optimization algorithms used in ML training including gradient descent variants

Model Interpretability: Experience with model interpretability techniques (SHAP, LIME) for explaining predictions

Privacy & Ethics: Understanding of ML ethics, fairness, bias mitigation, and privacy-preserving ML techniques

Research Background: Publications in ML conferences or journals, or active engagement with ML research community

Location: Portugal (100% Remote)