Intermediate Cloud AI & LLMOps Engineer (m/w/d)
Core
Design, operate, and optimize LLMOps pipelines for deploying, monitoring, and tracing Large Language Models (LLMs) within enterprise cloud environments.
Role type
Intermediate Cloud AI & LLMOps Engineer
Builds
Stable LLM deployment pipelines, monitoring/tracing systems, and optimized inference infrastructure for enterprise clients.
Domain
Cloud AI / LLMOps / Enterprise Software
Deliverable
production ML models
Required skills
LLMOps pipeline design (deployment, monitoring, evaluation, tracing), Cloud platforms (Azure, AWS, GCP) and AI services, Container orchestration (Docker, Kubernetes), CI/CD pipeline design, Infrastructure as Code (Terraform), Inference optimization (quantization, caching), AI FinOps (cost/token optimization), Security and compliance in cloud environments
Preferred skills
Experience bridging AI software development and traditional IT operations
Technologies
LangSmith, Arize Phoenix, Azure OpenAI Service, AWS Bedrock, Terraform, Docker, Kubernetes
Responsibilities
Design and maintain LLMOps pipelines for LLM deployment and monitoring; Optimize model performance and latency in production; Integrate cloud AI services with enterprise infrastructure; Monitor and optimize cloud infrastructure costs; Automate environment setup via IaC; Act as liaison between AI developers and IT operations teams
Seniority
Intermediate, hands-on IC
