technologies-expected :

technologies-optional :

responsibilities :

Deploying and maintaining machine learning models on Kubernetes clusters
Design, build, and maintain scalable infrastructure for training, testing, deploying, and monitoring ML models
Supporting a small team of data scientists and machine learning engineers in the maintenance and development of their infrastructure
Making suggestions on how to build new (or improve upon existing) data infrastructure solutions
Investigating and fixing arising problems on system, deployment, or application levels
Automate ML pipelines (data preprocessing, training, validation, and deployment)
Implement CI/CD, infrastructure as code, and best DevOps practices in ML environments
Ensure observability and reliability of deployed models (logging, metrics, tracing, alerts, performance monitoring)
Optimize resource usage and cloud costs
Support continuous improvement and introduce new tools and standards for the ML platform.

requirements-expected :

10 years of professional IT experience
Bachelor’s degree or higher in Computer Science or related field
Fluent in spoken and written English (minimum B2 level, mandatory)
Proven experience in MLOps and deploying machine learning models on Kubernetes (via e.g. MLflow, KServe, Ray, ollama, vLLM)
Experience in administering Linux OS
Knowledge how to build, operate and maintain container images
Familiarity with Azure DevOps, AKS, GKE, and Terraform for CI/CD and infrastructure as code
Strong understanding of cloud-native platform architecture and distributed system design
Experience with relational (PostgreSQL, MySQL) and NoSQL databases (MongoDB, Redis, Cassandra, Neo4j)
Proficiency in monitoring and observability tools (Prometheus, Grafana, loki, ELK stack or similar)
Familiarity with Agile methodologies (Scrum, Kanban) and DevOps/MLOps practices
Ability to design and implement data-driven applications using multiple programming languages (Python, C++, Java, R, JavaScript, C#)

offered :

technologies-optional :