Data Scientist

We are looking for a Senior Data Science Engineer to own an end-to-end fraud detection system, from data profiling and feature engineering to deployment, monitoring, and handover. You will build and maintain production models on high-volume event data, working directly with fraud analysts in a restricted client environment where data remains inside the network.

Required for this role

• 5+ years of experience in data science or ML engineering, including at least two production models that you deployed and maintained.
• Hands-on experience with fraud, anomaly, or abuse detection using high-volume event data, such as payments, telecom, ad fraud, or security logs.
• In-depth knowledge of gradient boosting and Isolation Forest, including calibration and threshold tuning for heavily imbalanced datasets.
• Experience with weak supervision, learning from noisy labels, and time-windowed feature engineering on streaming or micro-batch data.
• Practical knowledge of SHAP explainability and the ability to translate model outputs into clear rules for non-ML analysts.
• Strong Python and SQL skills, with end-to-end ownership of data profiling, ingestion, feature pipelines, model development, and production support.
• Experience with MLOps on virtual machines, including Docker, MLflow, scheduled pipelines, retraining workflows, and drift monitoring.
• Experience working through VPN in restricted client environments where data cannot leave the network, together with clear written English for presenting results directly to fraud analysts.
• Knowledge of telecom fraud, SIP signalling, CDRs, E.164 numbering, Wangiri, IRSF, or CLI spoofing, as well as graph features or community detection in caller-callee networks.
• Understanding of privacy and regulated model practices, including keyed hashing, pseudonymization, federated learning, GDPR, DPIA work, or regulated model documentation.

Your responsibilities

• Lead discovery with the pilot operator, profile the available data, and prepare a clear go/no-go report.
• Build the ingestion, tokenization, and time-windowed feature engineering pipeline.
• Train, evaluate, calibrate, and validate three fraud detection models on heavily imbalanced event data.
• Develop explainability outputs and convert model signals into readable rule suggestions for fraud analysts.
• Build the rule suggester, review API, and audit log required for analyst review and traceability.
• Package the production deployment, scheduled workflows, drift monitoring, and model retraining pipeline.
• Run the shadow pilot together with the client’s fraud analysts, review model behavior, and refine thresholds and rules.
• Maintain the deployed solution throughout the engagement and complete the technical handover.

What you get

Your time off

• 18 paid vacation days and 10 paid sick days annually
• 10 Ukrainian public holidays
• Maternity and paternity leaves
• Marriage and Parenthood Package
• Additional leave for major life events
• Sabbatical leave opportunities

Learning & growth

• Sombra University workshops and internal learning programs
• Tech Communities and knowledge sharing sessions
• Language courses and workshops
• Mentorship opportunities

Health & well-being

• Sports compensation or health insurance coverage
• Participation in races and marathons
• Corporate doctor (telemedicine)
• Well-being initiatives and workshops

And even more

• Company-provided technical equipment
• PE administration and tax support
• Internal referral program
• IT Club loyalty program
• Company events and volunteering initiatives

Before you apply

Our recruitment team will carefully review your profile, and if we see a good match with the role, we’ll reach out to you shortly.

If you don’t hear from us within 5 business days, it means we’ve decided to continue the process with other candidates for this position. Thanks for understanding.

Відгукнутись на вакансію