Staff Machine Learning Engineer

As a Staff Machine Learning Engineer in our Fraud Prevention team, you will leverage your expertise to build robust fraud detection models that safeguard our platform in the fast-paced world of online gaming and sports betting. Through innovative data analysis and cutting-edge tools, you’ll play a key role in ensuring platform security and enhancing our services for hundreds of thousands of daily users.

What you’ll you be doing:

• Fraud Detection Modeling
  • developing and optimizing traditional ML algorithms such as gradient boosted trees in fraud detection or anomaly detection domains
  • creating graph analyses and graph connection modelling
  • creating usable datasets for explorative analysis and turn clues into leads and insights for ML modelling
• Data Engineering
  • using SQL, Spark or Python for explorative analysis and feature engineering in a heavy tabular data environment
  • building new and supporting existing Erlang based microservices that enable product features
  • data engineering and working with relational DBs including data cleaning and preprocessing for ML pipelines and productionalization of the data pipelines using Snowflake, Airflow or DBT or similar tools
  • designing and implementing efficient ML pipelines
• Collaborative Innovation
  • creating impactful ML solutions and owing their implementation and improvements
  • autonomously breaking down and estimating data science projects into timed deliverables
  • working closely with cross-functional product and engineering teams
  • communicating complex findings to stakeholders in a clear, understandable manner
• Performance Tuning
  • optimizing models, continuously measuring and reacting to improve performance of ML solutions in production

We're looking for someone with:

• A Master’s degree (or equivalent) in Machine Learning, Data Science, Statistics, Mathematics, or a related field
• Minimum 4 years of real world experience
• Strong analytical background with proven expertise in exploratory data analysis, feature engineering, and working with tabular datasets
• Proficiency in Python (including libraries like Scikit-learn) and SQL, with solid experience in relational databases
• Good knowledge and experience of the broader data science domains, especially large language models or computer vision models used for anomaly detection
• A track record in deploying machine learning pipelines using tools such as Airflow, SageMaker Pipelines or similar
• A talent for clean coding, simple solutions, automated testing and continuous deployment
• A passion for working in the cloud and automation
• Excellent problem-solving skills and the ability to break down complex data science projects into achievable deliverables
• Investigative mindset and attentive eye that looks for clues in tabular, sequential datasets

Bonus points for:

• Experience with ML development and deployment tools such as ZenML, MLFlow, Airflow, …
• Experience with AWS Services such as EC2, EKS, Cloudformation, Cognito, …
• Experience with Kafka