WHO WE'RE LOOKING FOR

At Zingbrain, we build real-time personalization systems for iGaming platforms. Our models operate in production, influencing what each user sees — from game recommendations to sportsbook event suggestions — based on live behavioral, transactional, and contextual data.
We’re looking for a Senior Data Scientist to join our team and help us in the following areas:

• Develop ML-driven features for casino games using supervised learning (regression, ranking, classification)
• Maintain and enhance the existing recommendation systems in production, including:
  • Model enhancement using gradient boosting methods
  • Data cleaning and preprocessing
  • Pre- and post-processing workflows
  • Optimization of training and inference pipelines
  • Integration of ML models into Airflow pipelines in a multi-tenant environment
  • Adopt and configure the solution for different clients (tenants)

This is a hands-on role involving modeling, experimentation, and close collaboration with engineering and product teams in a high-load, real-time environment.

AS A PART OF OUR TEAM YOU WILL

• Collaborate with cross-functional teams of data scientists, engineers, product owners, designers, and researchers to ensure project success
• Analyze large datasets to extract actionable insights that inform product decisions
• Propose, implement, and evaluate machine learning approaches to solve business problems, work closely with Product Owner(s)
• Maintain and adopt the current recommendation solution in multi-tenant environment
• Influence product strategy through research and experimentation that deepens understanding of how product features, platforms, and promotions affect user behavior

WHAT WE EXPECT

Experience and education

• 5+ years of experience in data science
• A degree in a quantitative field (e.g., Mathematics, Statistics, Computer Science)

Core skills

• Proficiency in Python, SQL, and data manipulation tools (Pandas, Polars)
• Strong engineering skills to design, build, and maintain scalable ML solutions, including implementing observability across pipelines through metrics, logging, and alerting.
• Knowledge of Docker, Kubernetes.
• Ability to structure and solve loosely defined problems, delivering actionable insights for product development; Strong analytical mindset with both numerical and business understanding
• Hands-on experience with supervised ML techniques (regression and ranking using XGBoost, LightGBM, CatBoost, or neural networks), including feature engineering, model evaluation (AUC, NDCG, MSE, uplift metrics), and personalization or recommendation systems
• Proven experience deploying ML models to production for near real-time or batch processing
• Solid knowledge of statistical methods (A/B testing, significance testing, etc.)

Nice to have

• Production experience with large-scale recommendation systems
• Production experience with Airflow, Valkey/Redis, FastAPI
• Familiarity with contextual bandits or reinforcement learning for online optimization is a plus
• Familiarity with AutoML is a plus

WHAT THE HIRING PROCESS LOOKS LIKE

1. Application (15-30 minutes): Our Recruitment team will get familiar with your experience and skills and provide feedback on our decision regarding your application
2. Preliminary Call (15-30 minutes): Preliminary call serves as the first opportunity for us to learn more about your background, technical skills, and to answer any questions you might have about the role or company
3. Technical Interview (1 hr 30 mins): You’ll have a deep-dive discussion focused on your practical experience in data science and machine learning.
4. Soft-skill Interview (45-60 minutes): The last stage discussion centers around your fit with the company culture, your career ambitions and alignment with our team’s goals.
5. Offer Presentation (30-45 minutes): Once we've confirmed you're the right fit for the role, we'll prepare a job offer and present it to you. This includes all the details about your role, compensation, and the next steps to join our team.

The decision-making time between stages at our company typically spans 3 to 5 business days. However, some interviews or time intervals between interviews for decision-making may take more or less time than indicated, depending on the position, the candidate's specific experience, or other unforeseen circumstances. We are committed to maintaining a transparent and respectful hiring process, ensuring that all candidates are evaluated fairly and equitably. Additionally, we encourage candidates to ask questions at any stage of the process to clarify any concerns or requirements.