AI Agents Engineer

Zendesk; Berlin; Vor Ort; EUR 70.000 - 90.000; Vollzeit

Zusammenfassung

A leading technology company in Berlin is looking for a passionate AI Agent Engineer to innovate within their AI Agent system. Your role will involve designing robust, stateful AI agents using Python, while collaborating closely with cross-functional teams. Ideal candidates will possess a strong foundation in LLMs and tool integration, along with experience in performance optimization. The position emphasizes innovation in the chatbot and voice assistance landscape, providing a unique opportunity to shape the future of AI technologies.

Leistungen

Diversity and inclusion initiatives

Accommodations for disabilities

Qualifikationen

• Experience designing robust AI agents using Python.
• Familiarity with multi-agent architecture and LLM behavior.
• Basic understanding of evaluation frameworks for LLMs.

Aufgaben

• Design and develop scalable AI agents using modern frameworks.
• Collaborate with product managers to meet user needs.
• Document development processes for maintainability.

Kenntnisse

Python programming

LLM integration

Tool integration & APIs

Understanding of RAG

Performance optimization

Ausbildung

Bachelor's or Master's in Computer Science, AI, or related field

Tools

Fast API

LLM SDKs

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. In this role, you'll contribute to innovating at the forefront of AI technology, focusing on developing and refining intelligent, autonomous agents that leverage Large Language Models (LLMs) to streamline operations. You'll be a key player in implementing and improving the cognitive architecture for our AI-powered applications, creating systems that can reason, plan, and execute complex, multi-step tasks. You'll primarily focus on defined project scopes and tasks, working under the guidance of more senior team members.

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), contributing to the analysis of their strengths, weaknesses, and cost-effectiveness for specific use cases.

• Participate in the lifecycle of AI Agent deployment—collaborate closely with your immediate team, including 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 of multi-step, tool-using agents (e.g., LangChain, Autogen). Basic understanding of prompt engineering, context management, and LLM behavior (e.g., hallucinations).

• Tool Integration & APIs: Ability to integrate agents with external tools, databases, and APIs (e.g., OpenAI, Anthropic) in secure execution environments.

• Retrieval-Augmented Generation (RAG): Understanding of RAG pipelines with vector databases.

• Evaluation & Observability: Basic understanding of LLM evaluation frameworks and monitoring for latency and accuracy.

• Safety & Reliability: Awareness of prompt injection and basic concepts of implementing guardrails and fallback strategies.

• Performance Optimization: Basic understanding of managing LLM token budgets and latency.

• Planning & Reasoning: Familiarity with concepts of agents with long-term memory and planning capabilities.

• Programming & Tooling: Proficient in Python (Fast API) 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 mins
2. Interview with one member of the Hiring Team - 45 minutes
3. Take-home technical challenge
4. A technical interview with two of our developers to talk more in-depth about your technical experience and answer any questions you might have - 1 hour
5. Final interview with 2 of the following: CTO or Engineering Manager/Director - 45 minutes

Equal Employment Opportunity

Zendesk is an equal opportunity employer, and we’re proud of our ongoing efforts to foster diversity & inclusion in the workplace. Individuals seeking employment at Zendesk are considered without regard to race, color, religion, national origin, age, sex, gender, 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.

Zendesk endeavors to make reasonable accommodations for applicants with disabilities and disabled veterans pursuant to applicable federal and state law. If you are an individual with a disability and require a reasonable accommodation to submit this application, complete any pre-employment testing, or otherwise participate in the employee selection process, please send an e-mail to [e-mail] with your specific accommodation request.