Staff Machine Learning Engineer, AI Agent

Zendesk•San Francisco, CA

1d•Hybrid

About The Position

Join us at Zendesk, where we're on a mission to power exceptional service for every person on the planet. We're accelerating that ambition by building products rooted in AI, automation, and intelligent customer experiences, because behind every interaction lies an opportunity to make a human connection. We’re seeking a Staff Machine Learning Engineer to help build the AI Agent experiences that resolve customer issues with accuracy, speed, and trust. Your work will shape how AI agents reason through customer requests, use tools and business context, take action across systems, and collaborate with human agents when needed.

Requirements

Deep experience building production AI, automation, or intelligent product experiences that solve real customer problems.
Strong product engineering mindset — you care about the end-to-end user experience, not just the underlying model or system.
Experience designing agentic systems, conversational AI, workflow automation, retrieval-augmented experiences, or tool-using AI applications.
Ability to make complex AI systems reliable in production through evaluation, monitoring, debugging, and continuous improvement.
Strong technical judgment and the ability to lead ambiguous, cross-functional initiatives from concept to launch.
Comfort working across backend systems, product surfaces, data pipelines, APIs, and AI infrastructure.
Excellent collaboration and communication skills, with the ability to influence technical strategy across teams.
6+ years building production software, AI-powered products, or large-scale intelligent systems.
Experience leading technical design and execution for complex product or platform initiatives.
Hands-on experience with LLM-based applications, conversational systems, agent orchestration, retrieval systems, or AI workflow automation.
Strong programming skills in Python or equivalent backend languages.
Experience with production-quality systems, including APIs, distributed services, observability, testing, and reliability practices.
Familiarity with LLM evaluation, prompt and policy management, safety guardrails, tool calling, and feedback-driven improvement loops.
Experience mentoring senior engineers or setting technical direction across multiple teams.

Nice To Haves

Experience building AI agents, copilots, virtual assistants, or automated support products in production.
Experience with customer service, CRM, ticketing, knowledge management, or enterprise workflow products.
Background designing systems that combine structured business data, unstructured knowledge, and real-time user context.

Responsibilities

Lead the design and development of AI Agent capabilities that can understand customer intent, follow conversation context, take reliable actions, and deliver helpful resolutions.
Build agentic workflows that connect reasoning, retrieval, tool use, policy guidance, and human handoff into seamless customer support experiences.
Partner with product, design, engineering, and research teams to turn customer problems into polished AI-powered product features.
Improve the quality, reliability, and safety of AI Agent behavior through evaluation frameworks, feedback loops, observability, and iterative experimentation.
Design systems that enable AI Agents to use Zendesk data, knowledge, business rules, and third-party integrations effectively and securely.
Drive technical direction across teams, helping define patterns for scalable agent architecture, orchestration, testing, and production readiness.
Identify opportunities to improve resolution rates, reduce friction for customers and agents, and make AI-driven support feel natural, trustworthy, and useful.
Mentor engineers and raise the bar for technical execution, product thinking, and responsible AI development.