Darum lohnt es sich
Responsibilities Own the lifecycle of internal AI APIs, SDKs, and developer tooling to abstract LLM complexity Build and maintain CI/CD-integrated AI systems including code review automation and test generation pipelines Drive product development acceleration by integrating AI capabilities directly into existing collaborative workflows Design evaluation frameworks and automated testing pipelines to ensure quality of AI system outputs Build observability tooling to monitor model behavior, token costs, latency, and production output quality Establish shared prompt libraries and reusable context management systems Define and enforce engineering standards for AI system development Provide technical guidance and conduct architectural reviews of AI features Requirements 5+ years in software engineering, platform engineering, or infrastructure, with at least 2 years building production AI/ML systems Deep experience with LLM APIs and strong understanding of system behavior under real production load Experience building internal developer platforms, tooling, or shared infrastructure Proficiency in Python and at least one compiled language; comfortable across the full backend stack Preferred: Familiarity with agentic frameworks, RAG architectures, vector databases, or infrastructure-as-code (Terraform) Core Competencies Demonstrates expertise in building and maintaining AI systems, with a strong focus on LLM APIs, CI/CD integration, and automated testing frameworks.
Proficient in Python and backend development, with a solid understanding of production AI/ML system behavior and engineering standards. #J-18808-Ljbffr
