Senior Machine Learning Engineer
About this role
Dynamic pricing and recommender systems across mobile game portfolios require continuous model refinement and feature development to maintain optimal performance. Tripledot Studios seeks a Senior Machine Learning Engineer in London to build and improve training pipelines for these exact use cases, engaging over 25 million daily active users.
Working alongside monetization and product teams, this person will focus heavily on data understanding, feature engineering, and offline model evaluation rather than primary production deployment. Responsibilities include diagnosing model outcomes, investigating data and concept drift, and planning A/B tests to connect algorithmic decisions directly to revenue and player metrics.
An ideal candidate brings strong expertise in tabular machine learning models, relational databases, and cross-functional communication. Someone who thrives in an investigative environment, clarifies ambiguous requirements, and translates complex model results for non-technical partners will find a fitting home in this collaborative studio.
What you will do
- Build and improve training pipelines for dynamic pricing and recommender systems, handling feature design, label creation, training, tuning, and offline evaluation.
- Monitor live model performance across games and products while investigating data and concept drift tied to new titles, client versions, or user behavior.
- Diagnose missed model outcomes across training pipelines, business logic, and underlying data to restore overall model quality.
- Collaborate with monetization and product colleagues to connect model decisions to revenue and player outcomes and plan relevant A/B tests.
- Identify gaps in the team's understanding of models and propose improvements to project direction as familiarity with the business goals grows.
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 judging when offline results warrant an A/B test.
- Proficiency in SQL with the capability to write efficient queries for extracting, manipulating, and aggregating relational data.
- An investigative approach to handling incomplete data and longer-term requirements that need clarification.
- Capability to explain model results clearly 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 with 20 days remote working per year
- Daily free lunch with £12 allowance via JustEat when in the office
- Regular company events and quarterly on-site and off-site events
- Private medical cover with Bupa and health cash plan with Medicash
- Pension plan with qualifying earnings or opt-in 4% contributory match
Skills and tech stack
Questions candidates ask
What is the remote work policy for this role?
The position features hybrid working arrangements that include 20 days of remote working per year. Employees can work from anywhere in the world during these days or use them to cover mandatory office days.
What kind of machine learning models will I be working with?
The work involves tabular machine learning, including neural networks and approaches such as gradient-boosted decision trees. You will focus on dynamic pricing and recommender systems use cases.
What tools and frameworks are relevant for this position?
Relevant frameworks include PyTorch, PyTorch Lightning, TensorFlow, XGBoost, CatBoost, scikit-learn, and Ray, though no single framework is strictly required. Proficiency in SQL is also needed to extract, manipulate, and aggregate data.
How does the role interact with other teams?
You will collaborate closely with the monetization team and game product teams to plan A/B tests and translate product requirements into machine learning objectives. This includes explaining model results in terms of revenue and player outcomes.
The application is on the official Tripledot Studios careers page.
Apply on company site