Production ML Engineer: Real-Time Inference & MLOps

Zohorecruit; Polska; Hybrid; PLN 210,000 - 310,000; Full time

Job summary

Zohorecruit is seeking a highly experienced Machine Learning Engineer for a remote role. You will design, deploy, and maintain production-ready ML systems, taking models from experimentation to scalable, monitored environments.

Colaboration with Data Scientists, Data Engineers, and Platform teams is key to operationalizing ML models, building robust data pipelines, and implementing MLOps best practices.

Qualifications

• 4+ years in Machine Learning Engineering or Applied ML.
• Strong Python programming skills.
• Experience deploying models to production (APIs, batch, or streaming).
• Experience with Docker and containerized environments.
• Kubernetes experience for scaling ML services.
• Familiarity with ML Ops tools (MLflow, model registries).
• Solid preprocessing and feature engineering knowledge.
• Experience with AWS, Azure, or GCP.

Responsibilities

• Design and implement scalable ML systems for real-time and batch inference.
• Build deployment pipelines using containers and CI/CD.
• Develop APIs and services for serving ML models.
• Monitor model performance, drift, and data quality.
• Collaborate with Data Engineers on feature pipelines.
• Manage model versioning, reproducibility, and governance.
• Optimize inference performance and cloud costs.
• Support retraining workflows and continuous improvement.
• Ensure security and governance for data and models.

Skills

Machine Learning

Continuous Improvement

+18

Tools

Docker

Kubernetes

MLflow

CI/CD

Job description

Zohorecruit is seeking a highly experienced Machine Learning Engineer for a remote role. You will design, deploy, and maintain production-ready ML systems, taking models from experimentation to scalable, monitored environments.

Colaboration with Data Scientists, Data Engineers, and Platform teams is key to operationalizing ML models, building robust data pipelines, and implementing MLOps best practices.