machine learning engineer in mobile gaming

Описание

Tripledot Studios is one of the world’s largest independent mobile games companies. Its portfolio includes mobile games that reach top chart positions worldwide and engage over 25 million daily active users.

Задачи

Build and improve training pipelines for dynamic pricing and recommender system models, from feature and label design through training, tuning, and offline evaluation of tabular models; Monitor model performance across games and products, investigate data and concept drift, and make models easier to extend to other products; Diagnose missed model outcomes across the training pipeline, business logic, and underlying data, and implement improvements to restore model quality; Work with monetization and product colleagues to connect model decisions to revenue and player outcomes and plan A/B tests; Identify gaps in the team’s understanding of the models and propose improvements to their direction; Use AI-assisted development tools, including code assistants and LLM-based copilots, to accelerate implementation, debugging, and iteration while maintaining production-quality standards; Critically review and validate AI-generated code, model implementations, and infrastructure configurations for reliability, correctness, and maintainability; Explore AI-powered approaches to improve developer productivity or ML platform capability.

Требования

Hands-on experience training and evaluating tabular models using neural networks or gradient-boosted trees; Experience designing features and labels, choosing metrics for model decisions, and judging when offline results warrant an A/B test; Proficiency in SQL and ability to write efficient queries to extract, manipulate, and aggregate data from relational databases; An investigative approach to incomplete data and longer-term requirements that need clarification; Ability to explain model results to monetization and product partners in terms of revenue and player outcomes; Ability to participate in English meetings, read and write work documentation independently, and communicate clearly in English at B2 level or above; Nice to have: experience in ad tech, recommender systems, or online marketplaces; production APIs or ML model deployment; the Ray framework.

Условия

• 25 Days of paid holiday in addition to bank holidays
• 20 Remote working days per year, usable from anywhere in the world or to cover mandatory office days
• Regular company events and rewards
• Private medical cover
• Life and critical illness cover
• Family-forming and fertility support, subject to policy
• Employee Assistance Program
• Sport compensation
• Meal and transport vouchers
• English and Spanish classes
• Continuous professional development opportunities