Senior Machine Learning Engineer
About this role
Tripledot Studios is building dynamic pricing and recommender systems that support a portfolio of mobile games reaching over 25 million daily active users. The engineering team focuses on tabular machine learning, including gradient-boosted decision trees and neural networks, to power games played by millions globally. Day-to-day work centers on data understanding, feature development, and model improvement rather than heavy production deployment.
Incoming engineers collaborate closely with monetization and product groups to plan A/B tests and translate business needs into machine learning objectives. New hires typically spend their first three months learning project goals, contributing to training pipelines, and investigating data issues before taking a proactive role in directing model strategies. Individuals who thrive in this environment possess strong relational database skills, an investigative mindset when handling incomplete data, and the ability to connect quantitative results to player outcomes.
What you will do
- Design features and labels, train, tune, and evaluate tabular models including neural networks and gradient-boosted trees for dynamic pricing and recommender systems.
- Monitor live model performance across various games and products to detect anomalies.
- Investigate data and concept drift tied to new titles, client versions, or user behavior to make models easier to scale across products.
- Diagnose missed model outcomes across training pipelines, business logic, and underlying data to restore model quality.
- Partner with monetization and product teams to link model decisions to revenue and player outcomes while planning A/B tests.
- Propose improvements to model direction after identifying gaps in the team's understanding.
What you need
- Hands-on experience training and evaluating tabular models using neural networks or gradient-boosted trees.
- Demonstrated ability in designing features and labels, selecting appropriate metrics, and deciding when offline results warrant an A/B test.
- Proficiency in SQL with the capacity to write efficient queries for data extraction, manipulation, and aggregation from relational databases.
- An investigative approach to handling incomplete data and clarifying longer-term requirements.
- Capability to explain complex model results to monetization and product partners in terms of revenue and player outcomes.
Nice to have
- Experience in ad tech, recommender systems, or online marketplaces
- Experience with production APIs or deploying machine learning models
- Experience with the Ray framework
Benefits
- 25 days paid holiday in addition to bank holidays
- Hybrid Working 20 days remote working
- Private Medical Cover
- Life & Critical Illness Cover
- Family Forming Support
- Sport Compensation
Skills and tech stack
Questions candidates ask
What is the remote work policy?
The company offers hybrid working with 20 days of remote work. Employees can work from anywhere in the world or use the time to cover mandatory office days.
What machine learning frameworks are used?
The team works with tabular machine learning models including neural networks and gradient-boosted trees. Relevant tools include PyTorch, PyTorch Lightning, TensorFlow, XGBoost, CatBoost, and scikit-learn, though no single framework is required.
What are the expectations for the first few months?
New team members start by learning the project and business goals. Within the first three months, expectations include contributing to the training pipeline and investigating feature and model issues.
What benefits are provided?
Benefits include 25 days paid holiday, private medical cover, life and critical illness cover, family forming support, sport compensation, meal and transport vouchers, and language classes.
The application is on the official Tripledot Studios careers page.
Apply on company site