Erhalte eine Antwort von diesem Arbeitgeber — ein Lebenslauf und ein Anschreiben, die genau auf die Eigenschaften eingehen, die gesucht werden.
myitjob GmbH in Zurich is looking for an Applied AI Engineer to design and implement production-grade agentic systems. You will handle multi-agent orchestration, RAG pipelines, policy-based routing, tool invocation, and observability across the lifecycle.
The role requires extensive software engineering in production, hands-on experience with agentic frameworks, LLM API usage, and cloud-native tech such as Kubernetes, Docker, and Terraform.
Location: Zurich (office, remote or on client site)Workload: Full-timeStart: By agreementYour tasks:You design and build production-grade agentic systems end to end: multi-agent orchestration, RAG pipelines, policy-based routing, tool invocation, memory management and lifecycle observability.You build and own RAG pipelines covering embeddings, chunking strategy, vector search and context window engineering against real quality targets.You integrate and abstract across multiple LLM providers with fallback routing and token, cost and latency management.You implement LLMOps in production: eval harnesses with real quality metrics, prompt versioning, observability tooling, cost and safety monitoring.You embed directly with client engineering teams for workshops, proofs of concept, code-with sessions and architecture walkthroughs.You build reusable patterns, accelerators and playbooks that scale beyond a single engagement.You define and use metrics for agent accuracy, latency, safety and cost-effectiveness and present findings in business terms.Your profile:Extensive software engineering experience in production environmentsHands-on experience designing and deploying agentic AI solutions in production - non-negotiableDemonstrated experience with agentic orchestration frameworks such as LangGraph, CrewAI or AutoGen at production depthDirect experience calling LLM APIs in production code: provider abstraction, token management, latency and cost trade-offsRAG pipeline ownership: embeddings, chunking strategy, vector databases and context engineeringLLMOps fundamentals: eval harness design, prompt versioning and production observabilityCloud-native engineering maturity: Kubernetes, Docker, microservices, serverless, CI/CD and infrastructure as code with Terraform or HelmStrong Python; Java or an equivalent backend language is acceptableYour benefits:Flexibility to work from an office, remotely or directly with clientsExtensive learning and development opportunitiesDedicated mentoring and structured onboarding from day oneA workplace culture that celebrates diversity, inclusion and belonging