Описание
RED Global provides IT services and consulting. The company is seeking to turn ML prototypes into scalable, production-ready services through backend services, APIs, and infrastructure supporting machine learning models in production.
Задачи
•Productionise ML prototypes and deploy scalable services on Kubernetes
•Build and operate APIs for real-time and batch ML inference
•Manage GPU inference workloads, autoscaling, and performance
•Own service reliability, latency, load testing, and production incidents
•Build and maintain data pipelines and production monitoring
•Work with Applied Scientists to productionise new ML capabilities
Требования
•Strong experience with Java, Kotlin, or Scala and Python
•Hands-on experience with Kubernetes, Docker, and Infrastructure as Code
•Experience building and operating production HTTP APIs
•Strong AWS experience, including IAM, S3, and CI/CD
•Experience debugging live production systems
Nice to have: Triton, TorchServe or similar GPU inference platforms, Kafka, Spark or Databricks experience
Условия
•Fully remote within the European Union
•12-Month contract with extension possibilities
