MLOps Engineer

Webiks is looking for a MLOps Engineer!

Who are we?

Our mission at Webiks is to create powerful, data-driven applications and models that help our clients innovate and grow.

Who are you?

Join an advanced AI unit focusing on the development and implementation of models for satellite data analysis. The role bridges the gap between research and production, leading the full lifecycle of models – from the experimentation phase to operational deployment. The work includes building scalable MLOps infrastructures, automating training and inference processes, and continuously improving performance and reliability in distributed systems.

What will you do?

• uilding and leading end-to-end MLOps processes: Data → Training → Evaluation → Deployment → Monitoring.
• Developing model training pipelines, including experiment management and comparisons.
• Implementing and managing Model Registry, versioning, and artifact management (MLflow / DVC).
• Deploying models to production environments (batch / real-time inference).
• Working with distributed infrastructures (Ray / Kubernetes) for large-scale training and inference.
• Monitoring model performance (model performance, drift, data quality) and continuous improvement.
• Automating retraining and continuous evaluation processes.
• Collaborating with researchers, Data Engineers, and DevOps for a smooth transition from research to production.
• Optimizing performance (CPU / GPU) and costs.

Big Advantages

• Experience working with satellite data (EO / SAR).
• Familiarity with Ray, Airflow, or Prefect.
• Experience working with GPU workloads and model training optimization.
• Familiarity with observability tools (Prometheus, Grafana, OpenTelemetry).
• Experience with data versioning (DVC) or feature stores.
• Experience with real-time systems or operational systems.

• Experience in an MLOps / ML Engineer / Data Engineer role with an ML orientation.
• Proficiency in Python and experience with ML/DL libraries (PyTorch / TensorFlow).
• Experience in building pipelines for model training and inference.
• Experience with experiment tracking and model management tools (MLflow / W&B).
• Experience working with Docker and Kubernetes.
• Experience in cloud environments (AWS / GCP / Azure).
• Understanding of the model lifecycle and the challenges in transitioning to production.
• Ability to work in a multidisciplinary team in a dynamic environment.