SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Satori Analytics is a fast-growing scale-up of 100+ tech specialists delivering innovative data and AI solutions across industries including FMCG, retail, manufacturing, and financial services. The company covers the entire data lifecycle—from ingestion to AI applications—with cloud-based ecosystems and predictive models deployed globally.
You will design and maintain the infrastructure that takes ML models from experimentation to reliable, scalable production deployment. Your responsibilities include:
• Design and maintain production ML infrastructure, pipelines, and deployment patterns that enable models to move from experimentation to real business value
• Build automated ML workflows for training, evaluation, deployment, and retraining with versioning and reproducibility
• Deploy and serve models as production services across cloud, on-premise, or hybrid environments
• Monitor model performance, data drift, system health, and production signals to support retraining and troubleshooting
• Collaborate closely with Data Scientists, AI Engineers, and Software Engineers to improve testing, deployment, and maintenance practices
• Contribute to best practices around CI/CD, model registry, observability, security, and governance
• Support GenAI at scale, including LLM deployment, inference services, GPU optimization, and RAG infrastructure
• Ensure ML deployments follow strong security and operational resilience practices
The role offers a hybrid working arrangement with flexibility to work remotely from anywhere in the European Economic Area (EU, Switzerland) or UK for up to 6 weeks per year, with a modern Athens office as the primary location.
**Requirements:**
• BSc or MSc in Computer Science, Software Engineering, or related STEM field
• 5+ years of experience in MLOps, DevOps, platform engineering, or ML engineering with exposure to ML systems in production
• Strong Python skills and solid software engineering fundamentals
• Hands-on experience with ML lifecycle tools such as MLflow, Kubeflow, SageMaker, Vertex AI, Azure ML, or similar
• Experience deploying models using BentoML, TorchServe, Triton Inference Server, or equivalent serving frameworks
• Strong experience with Docker, Kubernetes, CI/CD, and production-grade deployment workflows
• Comfortable working across cloud environments (AWS, Azure, GCP, or hybrid setups)
• Experience with monitoring and observability tools such as Prometheus, Grafana, or similar
• Understanding of model performance, drift, retraining, reproducibility, and production reliability
• Strong collaboration skills across Data Science, Engineering, and client-facing teams
**Bonus qualifications:**
Terraform or Pulumi experience, feature stores (Feast, Tecton), data/model versioning (DVC, Delta Lake), Kafka or event-driven ML workflows, LLM serving (vLLM, TGI, Triton), model optimization (quantization, GPU tuning), RAG infrastructure and vector databases, LLM evaluation tools (LangSmith, RAGAS).
