ML engineer in social casino games

GamblingCareers.com; Barcelona; On-site; EUR 70,000 - 90,000; Full time

Job summary

Aristocrat ищет инженера по машинному обучению для поддержки команды MLOps: развитие и развёртывание ML-моделей от данных до продакшна, с фокусом на рекомендательные системы и игры. Работа предполагает тесное взаимодействие с Product/Data/Engineering.

Требуется опыт работы с Python, SQL и ML-библиотеками, а также владение Docker и инструментами отслеживания экспериментов. Приветствуется опыт в LLM/генеративных приложениях и разработке простых интерфейсов через Streamlit.

Qualifications

• 4+ лет опыта применения ML к реальным задачам
• Опыт в рекомендательных системах (collaborative filtering, ranking) применительно к реальным продуктам

Responsibilities

• Разработка, обучение, оценка и развёртывание ML-моделей с упором на рекомендательные системы
• Проектирование мониторинга производительности моделей: метрики, дрейф, качество данных, пороговые значения
• Участие в формировании культуры экспериментов и управлении версиями моделей (MLflow, Weights & Biases)
• Создание повторно используемых шаблонов и пайплайнов (Cookiecutter) и простых интерфейсов (Streamlit) для бизнес-пользователей

Skills

Python

SQL

Experiment tracking

Model deployment

Cloud platforms

Education

Quantitative field degree

Tools

scikit-learn

PyTorch/TensorFlow

XGBoost

MLflow

Weights & Biases

Docker

Airflow

Snowflake

LangChain

Job description

Описание:

At Aristocrat, we are driving technology in the gaming industry through modern, powerful solutions. Our mission is to bring joy to life through the power of play. We value collaboration, creativity and a strong commitment to excellence. This position will primarily support the Machine Learning area of our Product Madness business unit, a technology company specializing in social casino mobile games. We are looking for a Machine Learning Engineer to join our MLOps team and strengthen our modeling capabilities. You will be responsible for Machine Learning models end to end, from data and experimentation to production deployment.

Задачи:

Design, train, evaluate and retrain Machine Learning models, with a particular focus on recommendation systems, to support game features, improve the player experience and optimize operational efficiency. Lead the design of model performance monitoring: define which metrics and aspects should be monitored (drift, data quality, performance degradation), set thresholds and determine what it means for a model to remain reliable from a business perspective. Help establish a strong experimentation culture through model versioning and experiment tracking with tools such as MLflow or Weights & Biases, ensuring that experiments are reproducible and that different model versions can be easily compared and promoted. Contribute to developing a model governance culture: define how models are promoted to production and establish the foundations for communication and collaboration between the MLOps and Data Science teams. Create reusable templates and structures, such as Cookiecutter, to standardize how the Data Science team structures, delivers and communicates its models and experiments. Build robust training and feature engineering pipelines, and develop clean, production-ready code in Python and SQL. Explore and contribute to early-stage projects related to LLMs, RAG and Agentic AI when they add value, as a complement to the role and not as its primary responsibility. Develop simple interfaces, for example with Streamlit, to bring Machine Learning capabilities closer to non-technical users when useful. Collaborate with Product, Data and Engineering teams, clearly communicating results, limitations and recommendations to both technical and business audiences.

Требования:

More than 4 years of experience applying Machine Learning to real-world problems, from data processing to model deployment. Demonstrable experience with recommendation systems—such as collaborative filtering, ranking or similar techniques—applied to real products. Strong Python skills and hands-on experience with Machine Learning libraries such as scikit-learn, PyTorch/TensorFlow, XGBoost or similar. Strong SQL skills and experience working with large data warehouses. Hands-on experience with experiment tracking and/or model registry tools such as MLflow, Weights & Biases or equivalent. Experience designing or contributing to systems for monitoring and tracking model performance in production. Experience working with cloud platforms such as GCP, AWS or Azure, as well as Docker and Airflow. A strong analytical foundation, with education in a quantitative field such as mathematics, physics, computer science or engineering, or equivalent professional experience. Будет плюсом: Experience with Snowflake or other similar cloud data warehouses; Hands-on experience developing generative AI applications (LLMs), including API integration; Interest in or early experience with RAG systems, whether through prototypes, personal projects or professional experience; Interest in or familiarity with Agentic AI concepts or frameworks, such as LangChain Agents or CrewAI; Ability to develop simple user interfaces, for example with Streamlit, that bring Machine Learning models closer to other teams

Условия:

We offer a comprehensive compensation and benefits package designed to remain competitive in the market, support your well-being and recognize your contribution to our success. Our approach is based on a performance-based compensation philosophy, rewarding individual impact. Your specific compensation package will be determined based on factors such as your skills, experience, qualifications and location. Depending on your role and location, you may be eligible for annual bonuses and incentives, health and wellness benefits, paid time off, retirement plans, insurance coverage and other local benefits or benefits required by applicable law. Specific details about compensation and benefits for this position will be discussed during the selection process.