Join to apply for the Staff AI Agent Engineer (Machine Learning) role at Zendesk

Overview

The Agentic Tribe is revolutionizing the chatbot and voice assistance landscape with Gen3, a cutting‑edge AI Agent system that is goal‑oriented, dynamic, and truly conversational. Using a multi‑agent architecture and advanced language models, Gen3 can reason, plan, and adapt to user needs in real time, handling complex tasks and “off‑script” inquiries with ease.

About The Role

We’re seeking a highly experienced and influential AI Agent Engineer to drive innovation and technical leadership. You will design, develop, and deploy intelligent autonomous agents that leverage large language models (LLMs) to streamline operations, shape cognitive architecture, and guide other engineers.

Responsibilities

• Architect, design, and lead the development of robust, stateful, and scalable AI agents using Python and modern agentic frameworks such as LangChain and LlamaIndex.
• Strategize and oversee the integration of AI agent solutions with enterprise systems, databases, and third‑party APIs to create end‑to‑end workflows.
• Evaluate and select foundation models and services from vendors like OpenAI, Anthropic, and Google, assessing strengths, weaknesses, and cost‑effectiveness.
• Own the entire lifecycle of AI agent deployment, from concept to production, collaborating with product leadership and ML scientists.
• Troubleshoot, debug, and optimize complex AI systems for performance, reliability, and scalability, and mentor other engineers.
• 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 a culture of technical excellence.

Core Technical Competencies

• Expertise in LLM‑oriented system design, including multi‑step, tool‑using agents, prompt engineering, and advanced reasoning patterns.
• Mastery of tool integration & API design, delivering secure and scalable agent interactions with external tools, databases, and APIs.
• Experience with Retrieval‑Augmented Generation (RAG), vector databases, chunking, and hybrid search techniques.
• Leadership in LLM evaluation and observability, defining monitoring for latency, accuracy, and tool usage.
• Design and implementation of safety and reliability defenses such as prompt‑injection guardrails and fallback strategies.
• Performance optimization for token budgets and latency using model routing, caching (e.g., Redis), and other techniques.
• Planning and reasoning capabilities, including long‑term memory and complex planning methods such as ReAct or Tree‑of‑Thought.
• Expertise in Python, FastAPI, LLM SDKs, and cloud deployment with AWS/GCP/Azure, plus CI/CD for AI applications.

Preferred Qualifications

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

Interview Process

Step 1: Initial call with Talent Team (15 min)

Step 2: Interview with a hiring team member (45 min)

Step 3: Take‑home technical challenge

Step 4: Technical interview with two developers (1 hour)

Step 5: Final interview with Senior Director and Engineering Manager (45 min)

About Zendesk

Zendesk builds software for better customer relationships, empowering organizations to improve engagement and understand their customers. With over 100,000 paid customer accounts worldwide, Zendesk operates in the United States, Europe, Asia, Australia, and South America. Zendesk is an equal‑opportunity employer and is committed to diversity, equity, and inclusion.

Compensation and Benefits

Poland annualized base salary: zł392,000–zł588,000. Bonus, benefits, and other incentives are communicated during the offer stage. The role is hybrid, requiring in‑office attendance part of the week; the specific schedule will be determined by the hiring manager.

Equal Opportunity Employer

Zendesk is an equal‑opportunity employer. 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, disability, military or veteran status, or any other characteristic protected by applicable law.