AI Platform Engineer

Overview

AI Platform Engineer to operate, automate, and improve production AI services, focusing on reliable deployment and operations.

What you'll do

• Build and operate platforms for deploying, monitoring, and maintaining production AI models and services.
• Support model-serving environments, inference pipelines, deployment workflows, and release automation.
• Develop automation for model packaging, promotion, validation, rollout, rollback, and lifecycle management.
• Implement monitoring, logging, alerting, and observability for AI service performance, latency, availability, error rates, and cost.
• Troubleshoot model serving, API behavior, environment configuration, infrastructure, and deployment pipelines.
• Partner with teams to move AI workflows and services from prototype to production.

What you'll need

• Experience in MLOps, AI platform engineering, DevOps, software engineering, or production ML operations.
• Experience deploying or operating AI/ML models and inference services (or API-based production systems).
• Strong scripting or programming skills using Python or similar languages.
• Experience with containers, CI/CD, cloud environments, monitoring, and operational automation.
• Understanding of model deployment concepts, lifecycle management, versioning, validation, and rollback.
• Experience troubleshooting production systems across application, model, infrastructure, and deployment layers.

Nice to have

• Experience with model-serving frameworks and MLOps tools (e.g., Kubernetes, Docker, ECS, EKS, MLflow, KServe, BentoML, Ray, Airflow).
• Experience supporting LLMs/agentic workflows/RAG systems or other applied AI services (e.g., speech, translation).
• Experience with AWS services for compute, storage, networking, security, monitoring, and deployment.
• Experience evaluating or integrating commercial and open-source AI platforms.

Details

• Location in the source ATS line: DE, Germany, Home Office.