Staff AI Agent Engineer @ Zendesk

Zendesk; Berlin; Vor Ort; EUR 90.000 - 130.000; Vollzeit

Zusammenfassung

A leading software company in Berlin is seeking a Staff AI Agent Engineer to drive innovation in AI technology. The candidate will focus on designing intelligent, autonomous agents and implementing LLM systems that streamline operations. This role requires deep technical expertise, effective leadership, and the ability to influence teams and strategies. Experience in Python, cloud environments, and AI-related technologies is essential.

Qualifikationen

• Expert in designing complex multi-step agents.
• Mastery of secure tool integrations and APIs.
• Leadership in defining evaluation frameworks for LLMs.

Aufgaben

• Architect and lead the development of scalable AI agents.
• Oversee the integration of AI solutions with enterprise systems.
• Drive the lifecycle of AI Agent deployment from concept to production.

Kenntnisse

AI

Redis

React

Python

Cloud

FastAPI

AWS

GCP

Azure

Machine Learning

NLP

Ausbildung

Ph.D / Masters in a relevant field (e.g., Computer Science, AI, Machine Learning, NLP)

Jobbeschreibung

Job Description

The Agentic Tribe is revolutionizing the chatbot and voice assistance landscape with Gen3, a cutting‑edge AI Agent system that pushes the boundaries of conversational AI. Gen3 is goal‑oriented, dynamic, and truly conversational, capable of reasoning, planning, and adapting to user needs in real time. By leveraging a multi‑agent architecture and advanced language models, Gen3 delivers personalized and engaging user experiences, moving beyond scripted interactions to handle complex tasks and "off‑script" inquiries with ease.

We’re seeking a highly experienced and influential Staff AI Agent Engineer to join our team. In this role, you will drive innovation and technical leadership at the forefront of AI technology. Your focus will be on designing, developing, and deploying intelligent, autonomous agents that leverage large language models (LLMs) to streamline operations. You will shape the cognitive architecture for our AI‑powered applications, creating systems that can reason, plan, and execute complex, multi‑step tasks, and guide other engineers. You will own critical, cross‑cutting technical initiatives that impact multiple teams, serve as a go‑to expert for complex problems, and proactively engage with a broad range of stakeholders to influence strategy and execution.

The role requires deep technical expertise, leadership ability, and the capacity to translate strategic goals into scalable, production‑ready solutions.

About Zendesk

Zendesk builds software for better customer relationships, empowering organizations to improve engagement and understanding of their customers. Zendesk products are easy to use and implement, giving organizations flexibility to move quickly, focus on innovation, and scale with growth. With more than 100,000 paid customer accounts in over 150 countries, Zendesk operates across the United States, Europe, Asia, Australia, and South America.

Core Technical Competencies

• Expert in LLM‑Oriented System Design: Architecting and designing complex multi‑step, tool‑using agents (e.g., LangChain, Autogen). Deep understanding of prompt engineering, context management, and LLM behavior quirks (e.g., hallucinations, determinism, temperature effects). Ability to implement advanced reasoning patterns like Chain‑of‑Thought and multi‑agent communication.
• Mastery of Tool Integration & APIs: Designing and implementing secure and scalable integrations of agents with external tools, databases, and APIs (e.g., OpenAI, Anthropic) in complex execution environments, often involving novel solutions or significant architectural considerations.
• Retrieval‑Augmented Generation (RAG): Designing, building, and optimizing highly performant and robust RAG pipelines with vector databases, chunking, and sophisticated hybrid search techniques.
• Leadership in Evaluation & Observability: Defining, implementing LLM evaluation frameworks and comprehensive monitoring for latency, accuracy, and tool usage across production systems, influencing the observability strategy.
• Safety & Reliability: Designing and implementing state‑of‑the‑art defenses against prompt injection and robust guardrails (e.g., Rebuff, Guardrails AI) and complex fallback strategies.
• Performance Optimization: Deep expertise in managing LLM token budgets and latency through smart model routing, caching (e.g., Redis), and other advanced optimization techniques, identifying and addressing systemic performance bottlenecks.
• Planning & Reasoning: Designing and implementing cutting‑edge agents with long‑term memory and highly complex planning capabilities (e.g., ReAct, Tree‑of‑Thought).
• Programming & Tooling: Expert in Python, FastAPI, and LLM SDKs; extensive experience and strategic contributions with cloud deployment (AWS / GCP / Azure) and CI / CD for complex AI applications.

Responsibilities

• Architect, design, and lead the development of robust, stateful, and scalable AI agents using Python and modern agentic frameworks (e.g., LangChain, LlamaIndex), setting technical direction and best practices for engineering teams.
• Strategize and oversee the integration of AI agent solutions with existing enterprise systems, databases, and third‑party APIs to create seamless, end‑to‑end workflows across the product, identifying and mitigating architectural risks.
• Evaluate and select appropriate foundation models and services from third‑party providers (e.g., OpenAI, Anthropic, Google), analyzing their strengths, weaknesses, and cost‑effectiveness for specific use cases.
• Own and drive the entire lifecycle of AI Agent deployment, from concept to production and beyond for large, ambiguous, or highly complex initiatives—collaborate closely with cross‑functional teams, including product leadership and ML scientists to understand strategic needs and deliver highly effective agent solutions.
• Troubleshoot, debug, and optimize complex AI systems, ensuring exceptional performance, reliability, and scalability in production environments, and mentor other engineers in advanced problem‑solving techniques.
• Define, establish, and continuously improve platforms and methodologies for evaluating AI agent performance, setting key metrics, driving iterative improvements across the organization, and influencing industry best practices.
• Establish and enforce best practices for documentation of development processes, architectural decisions, code, and research findings to ensure comprehensive knowledge sharing and maintainability across the team and wider engineering organization.
• Mentor and guide more junior and mid‑level developers, fostering a culture of technical excellence and continuous learning, and contributing to the growth and career development of others.

Bonus Points (Preferred Qualifications)

• Ph.D / Masters in a relevant field (e.g., Computer Science, AI, Machine Learning, NLP).
• Comprehensive understanding of foundational ML concepts (attention, embeddings, transfer learning).
• Experience adapting academic research into production‑ready code.
• Familiarity with fine‑tuning techniques (e.g., PEFT, LoRA).

Requirements

AI, Redis, React, Python, Cloud, FastAPI, AWS, GCP, Azure, Machine learning, NLP