AI Agent Engineer (Machine Learning Engineer)

Zendesk; Berlin; Hybrid; EUR 70.000 - 90.000; Vollzeit

Zusammenfassung

A leading technology company in Berlin seeks a passionate AI Agent Engineer to develop and refine intelligent agents using Large Language Models (LLMs). The incumbent will contribute to building robust, scalable AI systems that streamline operations while collaborating with teams. This position offers a hybrid work model and the chance to work at the forefront of AI technology.

Qualifikationen

• Experience in developing autonomous agents with LLMs.
• Familiarity with AI deployment lifecycle.
• Ability to evaluate third-party model effectiveness.

Aufgaben

• Design and develop scalable AI agents.
• Evaluate foundation models for user needs.
• Collaborate with teams and troubleshoot AI systems.

Kenntnisse

Python

LLM behavior understanding

Context management

Integration with APIs

Prompt engineering

Ausbildung

Bachelor’s or Master’s in Computer Science, AI, Machine Learning, NLP

Tools

FastAPI

LangChain

LlamaIndex

Jobbeschreibung

Job Description

The Agentic Tribe is revolutionizing the chatbot and voice assistance landscape with Gen3, a cutting‑edge AI Agent system that’s pushing the boundaries of conversational AI. Gen3 isn’t your typical chatbot; it’s a goal‑oriented, dynamic, and truly conversational system 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.

About the Role

We’re seeking a passionate AI Agent Engineer to join our team and contribute to innovating at the forefront of AI technology. You’ll help develop and refine intelligent autonomous agents that leverage Large Language Models (LLMs) to streamline operations, implementing and improving the cognitive architecture for our AI‑powered applications and creating systems that can reason, plan, and execute complex multi‑step tasks.

Responsibilities

• Contribute to the design and development of robust, stateful, and scalable AI agents using Python and modern agentic frameworks (e.g., LangChain, LlamaIndex).
• Support the evaluation and selection of appropriate foundation models and services from third‑party providers (e.g., OpenAI, Anthropic, Google), analyzing strengths, weaknesses, and cost‑effectiveness for specific use cases.
• Participate in the lifecycle of AI Agent deployment and collaborate closely with product managers and software engineers to understand user needs for the features you’re building.
• Troubleshoot and debug AI systems to ensure optimal performance and reliability in production environments for assigned components.
• Document development processes, code, and findings to ensure knowledge sharing and maintainability within the team.

Core Technical Competencies

• Familiarity with LLM‑oriented system design, understanding multi‑step tool‑using agents (e.g., LangChain Autogen).
• Basic understanding of prompt engineering, context management, and LLM behavior (e.g., hallucinations).
• Ability to integrate agents with external tools, databases, and APIs (e.g., OpenAI, Anthropic) in secure execution environments.
• Understanding of Retrieval‑Augmented Generation (RAG) pipelines with vector databases.
• Basic understanding of LLM evaluation frameworks and monitoring for latency and accuracy.
• Awareness of prompt injection and concepts of implementing guardrails and fallback strategies.
• Basic understanding of managing LLM token budgets and latency.
• Familiarity with agents with long‑term memory and planning capabilities.
• Proficiency in Python (FastAPI) and LLM SDKs.

Bonus Points (Preferred Qualifications)

• Bachelor’s or Master’s in a relevant field (e.g., Computer Science, AI, Machine Learning, NLP).
• Understanding of foundational ML concepts (attention, embeddings, transfer learning).

Interview Process

1. Initial call with Talent Team – 15 minutes.
2. Interview with one member of the Hiring Team – 45 minutes.
3. Take‑home technical challenge.
4. Technical interview with two developers to discuss your experience – 1 hour.
5. Final interview with the CTO or Engineering Manager/Director – 45 minutes.

Location & Hybrid Requirements

Hybrid work model: this role requires attendance at our local office for part of the week, with flexibility to work remotely for the remaining days. The specific in‑office schedule will be determined by the hiring manager.

Employment Type: Full‑Time.

Equal Opportunity Employer

Zendesk is an equal‑opportunity employer and we are proud of our ongoing efforts to foster diversity and inclusion in the workplace. Individuals seeking employment at Zendesk are considered without regard to race, color, religion, national origin, age, sex, gender identity, gender expression, sexual orientation, marital status, medical condition, ancestry, physical or mental disability, military or veteran status, or any other characteristic protected by applicable law.