SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Tripledot Studios, one of the world's largest independent mobile games companies with 2,500+ employees across 12 studios and 25+ million daily active users, is seeking a Senior Machine Learning Engineer to join their monetization and product teams in Barcelona.
In this role, you will develop and improve machine learning models for dynamic pricing and recommender systems across Tripledot's game portfolio. The work focuses on tabular machine learning—neural networks and gradient-boosted decision trees—with emphasis on understanding data, feature engineering, and model improvement rather than production deployment ownership.
You will collaborate closely with monetization and game product teams to translate business requirements into ML objectives and plan A/B tests. The ramp-up is structured: within three months, you'll contribute to training pipelines and investigate features and model issues; by six months, you'll take a proactive role in setting model direction.
Key responsibilities include:
- Building and improving training pipelines for dynamic pricing and recommender models, covering feature and label design through training, tuning, and offline evaluation
- Monitoring live model performance across games, investigating data and concept drift, and extending models to new products
- Diagnosing performance gaps across the training pipeline, business logic, and data, then implementing improvements
- Connecting model decisions to revenue and player outcomes, collaborating with monetization and product teams on A/B test planning
- Identifying gaps in team understanding and proposing improvements to model direction
The position is hybrid based in Barcelona, with 20 days of remote work annually and 25 days paid holiday plus bank holidays.
REQUIREMENTS:
- Hands-on experience training and evaluating tabular models using neural networks or gradient-boosted trees (PyTorch, PyTorch Lightning, TensorFlow, XGBoost, CatBoost, or scikit-learn)
- Experience designing features and labels, selecting metrics for model decisions, and determining when offline results warrant A/B testing
- Proficiency in SQL with ability to write efficient queries for data extraction, manipulation, and aggregation from relational databases
- Investigative approach to incomplete data and requirements needing clarification
- Ability to explain model results to non-technical partners in terms of revenue and player outcomes
- Proficiency with AI-assisted development tools (code assistants, LLM-based copilots) while maintaining production-quality standards
- Ability to critically review and validate AI-generated code, model implementations, and infrastructure configurations
- Preferred: experience in ad tech, recommender systems, online marketplaces, production APIs, ML model deployment, or Ray framework
