Senior Data Scientist

At 365Scores, we're revolutionizing how fans receive and interact with live sports updates and data. Our platform combines the intensity of live sports with cutting-edge technology to deliver a personalized experience to millions of users worldwide.

As a Senior Data Scientist at 365Scores, you will be an integral part of our Machine Learning and AI team. The role is hands-on and impact-driven, focusing on building, improving, and delivering machine learning models that directly support business goals.

Requirements:

5+ years of experience with demonstrated impact in production ML systems
Experience with LLMs and agentic AI systems
Reinforcement learning for dynamic decision-making
Prior work on pricing optimization, revenue optimization, or real-time bidding systems
Contributions to open source ML projects or publications in relevant areas
Dynamic optimization systems that operate in production (pricing, bidding, allocation)
ML systems where predictions drive automated business decisions
Real-time models that adapt based on incoming data and feedback
End-to-end ownership of ML projects from problem formulation to production impact
Advanced degree (MS/PhD) in quantitative field, or equivalent depth through industry experience
Translates ambiguous business problems into rigorous mathematical frameworks
Owns projects independently from conception through production deployment
Mentors other team members on ML best practices

Responsibilities:

Deep expertise in mathematical optimization (convex optimization, constrained optimization, gradient-based methods)
Hands-on experience with Bayesian optimization, hyperparameter optimization, or similar techniques
Strong foundation in causal inference (propensity scoring, uplift modeling, causal ML, or experimental methods)
Advanced time series modeling and forecasting for decision-making systems
Proven ability to architect and train deep neural networks (PyTorch or TensorFlow) for complex problems
Experience applying ML/DL to optimization problems (pricing, bidding, resource allocation, sequential decisions)
Track record of improving model performance through rigorous experimentation
Demonstrated success deploying and maintaining ML models in real-time production environments
Experience building end-to-end ML pipelines from data ingestion to model serving to monitoring
Proficiency with MLOps practices: experiment tracking, model versioning, A/B testing, performance monitoring
Expertise with model serving at scale and handling production incidents