Mission

The enterprise software landscape is fracturing. We are transitioning from "Systems of Record" to "Systems of Action." Zendesk is leading this shift with the Resolution Platform, aiming to be the first CX company to secure $1B in AI-driven revenue. To achieve this, we must solve the "Orchestration Trap." We are not just building features; we are building the high-performance runtime that allows fleets of AI Agents to perceive, reason, and act.

Role Overview

As a Senior-Level AI Engineer at Zendesk, you will work on cutting-edge large language models, planning algorithms, and multi‑agent coordination. Your work will enable AI agents to bridge the gap between offline model capabilities and dynamic, real‑world task execution.

Responsibilities

- Architect and research the world’s best task agents, optimizing agentic workflows to achieve state‑of‑the‑art performance on complex multi‑step tool‑use benchmarks.
- Design advanced memory and cognitive architectures inspired by human cognition to allow agents to filter interference, maintain context, and leverage long‑term knowledge across extended interactions.
- Analyze agentic AI trajectories and refine reasoning, capturing chain‑of‑thought, detecting anomalies, and preventing hallucination loops.
- Build scalable, autonomous self‑improving loops so agents can learn continuously without human intervention, including skill discovery and tool‑search refinement.
- Develop enterprise guardrails and content safety mechanisms to protect against tool misuse, cascading action chains, and unintended control amplification.
- Implement supervisor patterns and governance architectures to regulate actions, enforce capability‑based access,



and align with compliance standards such as the NIST AI Risk Management Framework.
- Create continuous, multi‑turn evaluation frameworks and preference data pipelines for rigorous, real‑world agent assessment.

Qualifications

- Senior‑level experience as an AI engineer with deep expertise in machine learning, transformer architectures, and applied agentic systems.
- Proven track record designing real‑world AI applications that use agentic frameworks for reliable, multi‑step automated workflows.
- Strong background in cognitive systems, safety, and policy enforcement within AI loops, with the ability to decompose high‑level goals into actionable, verifiable sub‑tasks.
- Data‑driven evaluation mindset, able to reduce distribution mismatch between sandbox and production environments while managing ambiguity.
- Proficiency with Python, PyTorch, and applied agent frameworks such as LangChain or LangGraph, plus experience with custom LLM simulators and continuous evaluation environments.

EEO Statement

Zendesk is an equal chance employer and we’re proud of our ongoing efforts to foster global diversity, equity, & inclusion in the workplace. Individuals seeking employment and employees 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. Zendesk is an AA/EEO/Veterans/Disabled employer. We endeavor to make reasonable accommodations for applicants with disabilities and disabled veterans pursuant to applicable federal and state law.

#J-18808-Ljbffr

📌 Senior Machine Learning Engineer (Melbourne)
🏢 Zendesk(Australia
📍 Melbourne