Job Description

Team: AI Agents |Location: Melbourne / Sydney

What we have built

We run production AI agents that autonomously resolve customer service tickets across 100,000+ Zendesk accounts. Each agent takes a customer issue, decomposes it into a multi-step plan, executes real actions refunds, order modifications, escalations through live APIs, and closes the ticket without a human in the loop.

The core uses a proprietary iterative architecture: goals decompose into plans, reusable skills are pulled from a registry, execution is evaluated, and the result feeds the next attempt. Successful resolution patterns are synthesised into new skills and written back into the registry the system learns from its own execution history.

On GAIA-class multi-step tool-use benchmarks, our agents match the best published results. Internally, 158+ scenario-based evals run continuously against real Zendesk tickets, scored through Braintrust with regression detection on every deploy.

What you will own

• Architecture: The iterative planner works. What we have not solved: plan decomposition under ambiguous goals, memory-tier interference across concurrent sessions, over-eager skill acquisition, and multi-agent delegation via A2A. These are yours to take on.

• Domain-specialised training: We are building toward RL-trained models specialised for customer service resolution. The data pipeline is instrumented. The next step reward curricula, rollout systems, feedback loops is a 6–12 month build. You own both the science and the systems.

• Evaluation infrastructure: 158+ evals run continuously, but multi-turn evaluation and automated trajectory analysis are early. You will build the quality gates that block deploys when performance drops, integrated into CI from the start.

• Guardrails at scale: Tool misuse, cascading action chains, prompt injection, hallucination loops: the threat surface for autonomous agents at enterprise scale is real. You will design the multi-layered defences supervisor patterns, capabilities-based access control, output validation that work across thousands of concurrent sessions without adding latency.

What we are looking for

• 5+ years building production ML/AI systems. You have shipped agent architectures that handle planning, tool dispatch, memory, and failure recovery. If your experience is Lang Chain tutorials, this is not the right fit.

• You have built internal evals because you know why public benchmarks lie, and you have the scars to prove it.

• Python and Py Torch fluency, plus at least one agent framework and the judgment to know when to throw it out and build custom.

• Bonus: genuine depth in RL for language models reward shaping, online/offline tradeoffs, reward hacking as a diagnostic. We are building toward domain-specialised training and need someone who can lead that work.

The intelligent heart of customer experience

Zendesk software was built to bring a sense of calm to the chaotic world of customer service. Today we power billions of conversations with brands you know and love.

Zendesk believes in offering our people a fulfilling and inclusive experience. Our hybrid way of working, enables us to purposefully come together in person, at one of our many Zendesk offices around the world, to connect, collaborate and learn whilst also giving our people the flexibility to work remotely for part of the week.

As part of our commitment to fairness and transparency, we inform all applicants that artificial intelligence (AI) or automated decision systems may be used to screen or evaluate applications for this position, in accordance with Company guidelines and applicable law.

Zendesk is an equal opportunity 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. We are an AA/EEO/Veterans/Disabled employer. If you are based in the United States and would like more information about your EEO rights under the law, please click here.

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 peopleandplaces@zendesk.com with your specific accommodation request.