Senior AI Agent Engineer

Zendesk

full-time

Posted on: 9/16/2025

Origin: • 🇩🇪 Germany

✨ AI Apply

Senior

AWSAzureCloudGoogle Cloud PlatformPythonReactRedis

About the role

Design and develop robust, stateful, and scalable AI agents using Python and modern agentic frameworks (e.g., LangChain, LlamaIndex).
Integrate AI agent solutions with existing enterprise systems, databases, and third-party APIs to create seamless, end-to-end workflows.
Evaluate and select appropriate foundation models and services from third-party providers (e.g., OpenAI, Anthropic, Google) and analyse cost-effectiveness.
Drive the entire lifecycle of AI Agent deployment in collaboration with product managers, ML scientists, and software engineers.
Troubleshoot, debug, and optimize complex AI systems to ensure optimal performance, reliability, and scalability in production environments.
Establish and improve platforms for evaluating AI agent performance, defining key metrics to measure success and guide iteration.
Document development processes, architectural decisions, code, and research findings to ensure knowledge sharing and maintainability across the team.

Experience designing, developing, and deploying intelligent, autonomous agents that leverage LLMs
Expert in Python and modern agentic frameworks (e.g., LangChain, LlamaIndex)
Experience with FastAPI and LLM SDKs
Experience integrating agents with enterprise systems, databases, and third-party APIs
Experience evaluating and selecting foundation models/services (OpenAI, Anthropic, Google)
Deep understanding of prompt engineering, context management, and LLM behaviour quirks (e.g., hallucinations, determinism, temperature effects)
Experience implementing advanced reasoning patterns (Chain-of-Thought, ReAct, Tree-of-Thought) and multi-agent communication
Experience building and optimizing RAG pipelines with vector databases, advanced chunking, and hybrid search
Experience implementing LLM evaluation frameworks and monitoring for latency, accuracy, and tool usage
Knowledge of prompt injection defenses and guardrails (Rebuff, Guardrails AI) and fallback strategies
Experience managing LLM token budgets and latency through model routing and caching (Redis)
Cloud deployment experience (AWS/GCP/Azure) and CI/CD for AI applications
Preferred: Ph.D. or Masters in relevant field; familiarity with fine-tuning techniques (PEFT, LoRA); deep foundational ML knowledge