Job Description
TyrAds is a mobile performance marketing agency specializing in user acquisition and monetization for global app advertisers and developers, with a focus on rewarded advertising. Our rewards platform reaches over 40 million monthly active users worldwide, driving improved retention, engagement, and ROAS. By leveraging hyper-personalization, live operations, and AI-powered recommendations, our simple yet unique solution has supported 150+ global partners across 10+ countries, including Scopely, Huuuge Games, and NetEase, fostering sustainable growth together.
We're hiring a Data Scientist who can ship real-time ML systems and also evaluate and improve them after launch. You'll work on scoring models, recommendations, fraud/risk signals, and the data pipelines behind them.
What You'll Do
- Analytics & Iteration
- Investigate funnel and performance issues, find patterns, propose fixes
- Design and analyze experiments (A/B tests, holdouts)
- Build post-launch evaluation
- Turn findings into clear recommendations for product/engineering stakeholders
- Real-time ML in Production
- Build and deploy real-time scoring/recommendation models (not just notebooks)
- Work with latency constraints (optimize p95/p99, payload size, feature fetch time)
- Implement robust serving
- Ensure training/serving consistency
- Monitoring & Model Health
- Set up monitoring for live models: data drift, prediction drift, performance decay
- Define guardrails and alerts
- Recommend improvements (features, thresholds, retraining cadence)
Must Have
- Production ML
- Deployed real-time ML models behind an API
- Debugged latency issues, optimized inference
- Familiar with monitoring/observability for ML systems
- Technical
- 3+ years in DS/ML
- Strong Python (pandas, numpy, scikit-learn)
- Strong SQL (CTEs, window functions, large tables)
- Classification models (XGBoost/LightGBM) and evaluation (AUC, precision/recall)
- Analytics
- A/B testing experience (design, analysis, avoiding bias)
- Can communicate insights clearly and drive decisions
- Engineering
- Git + Docker basics
- Clean, maintainable code
Nice to Have
- Fraud detection
- Databricks / Spark
- Feature stores, MLflow, or similar
Location: Office in Bali
