ML Ops Engineer, KI Group

• You’re a ML Ops Engineer who’s not afraid to get deep into infra. You understand what it takes to ship AI-powered features to production, and you take pride in building systems that just work
• Experience deploying LLMs or RAG pipelines in production
• Strong experience with Docker, CI/CD pipelines (GitHub Actions, GitLab CI, etc.), and cloud infrastructure (AWS, GCP, or Azure)
• Solid understanding of ML Ops workflows, including model packaging, deployment, and serving
• Experience with logging, tracing, monitoring, and metrics (Prometheus, Grafana, Sentry, etc.)
• High autonomy — you’re comfortable owning infra and deployment from day one

Desirable

• As a ML Ops Engineer, you’ll be the backbone of our technical infrastructure — owning the delivery pipeline, model serving stack, and runtime systems that power our AI workflows
• Your mission: ensure that our AI agents, APIs, and web interfaces are reliable, scalable, and fast, from prototype to production
• Build and maintain backend APIs and services to support AI-driven features and workflows
• Own our ML Ops pipeline: from model versioning and testing to containerized deployment and CI/CD
• Set up observability and monitoring for LLM-based services and agentic systems
• Manage infrastructure for fine-tuning, retrieval-augmented generation (RAG), and real-time agent orchestration
• Collaborate closely with AI engineers to streamline model integration, scaling, and latency optimization
• Contribute to frontend features and internal tooling as needed — you’re not afraid of building end-to-end
• Automate everything you can — and keep our infrastructure lean, secure, and maintainable