machine learning engineer

Empat provides IT services and consulting, focusing on the development and scaling of production machine learning systems for real-time personalization and decision-making.

• Build and productionize ML models for ranking, personalization, and customer engagement;
• Develop pipelines that transform behavioral, demographic, and contextual signals into online and offline features;
• Design and deploy low-latency APIs and decision services for real-time decision-making;
• Implement experimentation frameworks, including A/B testing and exploration-exploitation strategies;
• Operationalize the ML lifecycle, including automated training, CI/CD for models, artifact and feature versioning, and online/offline parity;
• Build observability into ML systems by monitoring data quality, model drift, and decision outcomes, and triggering retraining;
• Establish closed feedback loops that connect decisions to business outcomes;
• Collaborate with product and engineering teams to balance personalization, compliance, and business value.

• 5+ Years of experience in applied ML engineering in recommendation, personalization, ranking, or advertising systems;
• Strong proficiency in Python or Go, SQL, and modern ML frameworks such as TensorFlow or PyTorch;
• Strong understanding of MLOps best practices, including CI/CD for ML, Docker, Kubernetes, Airflow, Kubeflow, model registries, and monitoring frameworks;
• Familiarity with cloud ML platforms like Vertex AI or SageMaker and data warehouses like BigQuery, Snowflake, or Redshift;
• Experience deploying real-time ML systems, including low-latency serving, feature stores, and event-driven architectures;
• Understanding of multi-objective optimization and trade-offs in personalization systems;
• Comfortable working cross-functionally in a dynamic startup environment with overlap within USA time zone;
• Fluent English (spoken and written);
• Nice to have: Experience in martech, adtech, CRM, or large-scale personalization platforms, exposure to bandit algorithms, reinforcement learning, or causal inference, experience building systems serving millions of users at scale, hands-on experience with Google Cloud Platform (GCP), familiarity with observability tools such as Prometheus, Grafana, Evidently, WhyLabs, or Great Expectations.

• Competitive salary;
• Medical insurance;
• Supportive onboarding and trial period;
• Team-building events, including parties, online activities, and picnics;
• Modern office in Kyiv with generator and battery backup.