Senior Platform Engineer AI & Observability (m/f/d)
Core
Design, deploy, and operate scalable AI, observability, and cloud-native platforms based on Kubernetes and HPC technologies.
Role type
Senior Platform Engineer (AI & Observability)
Builds
AI services, LLM inference platforms, GPU-enabled workloads, and federated research infrastructures
Domain
Research computing, AI/ML infrastructure, Cloud-native
Deliverable
production ML models
Required skills
Kubernetes, Linux, Docker, Python, Go, Bash, DevOps, MLOps, observability, monitoring, logging, tracing, security
Preferred skills
LLM inference frameworks (vLLM, Triton, Ollama, Llama.cpp), GPU-accelerated environments, Prometheus, Grafana, Helm, GitOps, CI/CD, RAG architectures, vector databases, AI agents, security monitoring tools (Falco, Tracee)
Technologies
Kubernetes, Docker, Prometheus, Grafana, Helm, vLLM, Triton, Ollama, Llama.cpp, Falco, Tracee
Responsibilities
Design and operate scalable AI and observability platforms; Build and optimize AI services and LLM inference platforms; Develop monitoring, logging, and security solutions; Create standardized deployment workflows and automation; Enable reliable multi-tenant operation of research infrastructures; Provide technical leadership in architecture and operations
Seniority
Senior, hands-on IC
