Staff AI Agent Engineer

Zendesk; Bremen; Hybrid; EUR 75.000 - 95.000; Vollzeit

Zusammenfassung

A tech company in Bremen is seeking a Staff AI Agent Engineer to drive innovation in AI agent systems. The ideal candidate will possess extensive knowledge in LLM-oriented design and tools like Python and FastAPI, ensuring effective integration of advanced AI solutions. This role offers a hybrid work environment, combining remote and in-office collaboration, and requires a Ph.D. or Master’s in a relevant field along with solid experience in the industry.

Qualifikationen

• Ph.D. or Master’s in Computer Science, AI, Machine Learning, or NLP.
• Comprehensive understanding of foundational ML concepts.
• Experience adapting academic research into production-ready code.
• Familiarity with fine-tuning techniques.

Aufgaben

• Architect, design, and lead development of scalable, stateful AI agents.
• Strategize and oversee integration of AI agent solutions.
• Evaluate and select foundation models and services.
• Own the entire lifecycle of AI Agent deployment.
• Troubleshoot, debug, and optimize complex AI systems.
• Define, establish, and continuously improve platforms for evaluation.
• Establish and enforce best practices for documentation.
• Mentor and guide junior and mid-level developers.

Kenntnisse

Expert in LLM-oriented system design

Mastery of tool integration & APIs

Retrieval-Augmented Generation (RAG)

Leadership in evaluation & observability

Safety & reliability

Performance optimization

Planning & reasoning

Programming & tooling

Ausbildung

Ph.D. or Master’s in Computer Science, AI, Machine Learning, or NLP

Tools

Python

FastAPI

AWS

GCP

Azure

Jobbeschreibung

Job Summary

The Agentic Tribe is revolutionizing chatbot and voice assistance by building Gen3, a goal‑oriented, dynamic AI Agent system that can reason, plan, and adapt to user needs in real‑time. We are seeking a Staff AI Agent Engineer to drive innovation and technical leadership, design and deploy intelligent autonomous agents leveraging large language models (LLMs), and guide cross‑team engineering efforts.

Responsibilities

• Architect, design, and lead development of scalable, stateful AI agents using Python and modern agentic frameworks (e.g., LangChain, LlamaIndex).
• Strategize and oversee integration of AI agent solutions with existing enterprise systems, databases, and third‑party APIs to create seamless end‑to‑end workflows.
• Evaluate and select foundation models and services from providers such as OpenAI, Anthropic, or Google, analyzing strengths, weaknesses, and cost‑effectiveness.
• Own the entire lifecycle of AI Agent deployment, from concept to production and beyond, collaborating closely with product, ML scientists, and other stakeholders.
• Troubleshoot, debug, and optimize complex AI systems to ensure performance, reliability, and scalability in production.
• Define, establish, and continuously improve platforms and methodologies for evaluating AI agent performance, setting key metrics and driving iterative improvements.
• Establish and enforce best practices for documentation of development processes, architectural decisions, code, and research findings.
• Mentor and guide junior and mid‑level developers, fostering technical excellence and continuous learning.

Core Technical Competencies

• Expert in LLM‑oriented system design: complex multi‑step, tool‑using agents; advanced prompt engineering; chain‑of‑thought and multi‑agent communication patterns.
• Mastery of tool integration & APIs: secure and scalable integrations with external tools, databases, and APIs.
• Retrieval‑Augmented Generation (RAG): design, build, and optimize robust RAG pipelines with vector databases and hybrid search techniques.
• Leadership in evaluation & observability: LLM evaluation frameworks, comprehensive monitoring for latency, accuracy, and tool usage.
• Safety & reliability: defenses against prompt injection and robust guardrails (e.g., Rebuff, Guardrails AI).
• Performance optimization: token budget and latency management through model routing, caching, and optimization techniques.
• Planning & reasoning: agents with long‑term memory and complex planning capabilities (e.g., ReAct, Tree‑of‑Thought).
• Programming & tooling: Python, FastAPI, LLM SDKs, cloud deployment (AWS/GCP/Azure), CI/CD for complex AI applications.

Preferred Qualifications

• Ph.D. or Master’s in Computer Science, AI, Machine Learning, or NLP.
• Comprehensive understanding of foundational ML concepts (attention, embeddings, transfer learning).
• Experience adapting academic research into production‑ready code.
• Familiarity with fine‑tuning techniques (PEFT, LoRA).

The 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 – 1 hour.
5. Final interview with either the CTO or Engineering Manager/Director – 45 minutes.

Hybrid: The role is hybrid; the employee must attend the local office part of the week. The specific in‑office schedule will be determined by the hiring manager.

EEO Statement

Zendesk is an equal opportunity employer and we’re proud of our ongoing efforts to foster diversity & inclusion in the workplace. Applicants and employees are considered without regard to race, color, religion, national origin, age, sex, gender, gender identity, sexual orientation, marital status, medical condition, ancestry, disability, military or veteran status, or any other characteristic protected by applicable law. We are an AA/EEO/Veterans/Disabled employer.