About Spyke Games
We are a leading mobile gaming company founded by gaming veterans who have built and scaled massive gaming businesses for the past decade.
We want to build the next generation of mobile game franchises to be played by millions of people around the globe for years. We are bringing together the smartest, the most talented and ‘fun to work with’ group of people united around this single mission. Fostered with team spirit and collaboration, we strive to create a passionate, energetic and eager to learn “geek” culture focused on games.
We’re looking for a Data Scientist to help build, grow and optimize our mobile games. At Spyke, you will be working in a fast-paced, hyper-growth environment with some of the smartest minds in the industry. This scale and pace comes along with very interesting business challenges which we will solve together, using a technology-agnostic and data-informed decision making approach.
Job Responsibilities
- Build and productionize ML models that drive product and marketing decisions — player segmentation, player behavior prediction, and growth modeling.
- Design personalization and optimization systems that decide what each player sees, and the decision logic behind them — not just the prediction.
- Own your pipelines in production. Build and maintain ETL and model workflows on our orchestration stack, and keep them healthy with monitoring, data quality checks and alerting.
- Design and run experiments. Define test groups, choose the right metrics, evaluate results honestly, and drive the decision together with the product and marketing teams.
- Run exploratory analysis on player and monetization data to find scalable ways to improve engagement, retention and revenue — and turn findings into a concrete, shippable action.
Job Requirements
- Degree in Engineering, Statistics or a related quantitative field.
- 1+ years of hands-on data science or Python development experience, with code that reached production
- Strong Python, with clean, reviewable, maintainable code. Comfortable with Git and code review.
- Strong SQL and real experience with a columnar cloud warehouse — BigQuery preferred.
- Practical ML depth in supervised learning on tabular data: gradient boosting, classification and regression, proper validation, class imbalance, feature engineering and model interpretability.
- Experience in data engineering and familiarity with tools such as GCP, Apache Airflow, Docker, Flask.
- Statistics and experimentation fundamentals: hypothesis testing, confidence intervals, sample size.
- Effective use of AI tools in your daily workflow, with the judgment to review and validate what they produce rather than shipping it blindly.
