MLOps / ML Infrastructure Engineer

• Build and own the ML execution and infrastructure layer used by product services.
• Develop high-load Python systems for ML inference, training, and data processing.
• Work closely with research/backend engineers to integrate ML systems into production APIs.
• Design distributed pipelines and task queues for batch and streaming workloads.
• Work on GPU inference, scaling, and throughput optimization.
• Maintain the MLOps layer: deployment, updates, and monitoring of models and services.
• Set up and support CI/CD pipelines for services and ML workflows.

Do you have experience in Terraform?, * 5+ years of commercial Python development experience.

• Strong Python skills (performance, async, multiprocessing).
• Experience building and operating high-load production systems.
• Understanding of production ML inference (latency, reliability, cost).
• Hands-on experience with Docker, Kubernetes, and IaC frameworks like Terraform.