Zendesk is looking to improve its Customer Experience by building a foundation that powers every AI-driven experience, enabling product teams to build, evaluate, and deploy state-of-the-art Large Language Model (LLM) applications reliably and at scale.
Requirements
- 2–4 years of hands-on experience developing and deploying ML systems or infrastructure.
- Familiarity with LLM applications, vector databases, or ML/AI infrastructure components.
- Exposure to AWS, GCP, or Azure; understanding of Kubernetes, Docker, or similar containerized environments.
- Proficiency in Python and familiarity with at least one other backend language (Java, Scala, Golang, or Ruby).
- Understanding of CI/CD workflows, testing frameworks, and software design principles.
- Experience building small-scale ML services or APIs.
- Exposure to ML observability tools and evaluation frameworks.
Responsibilities
- Contribute to the development of Zendesk’s LLM Proxy, enabling secure, cost-optimized access to multiple foundation models.
- Help develop and maintain benchmarking and A/B testing frameworks for measuring LLM performance, latency, and cost.
- Assist in building orchestration systems that enable multi-step, tool-using AI agents.
- Work closely with applied ML, product, and platform teams to ensure infrastructure meets product needs.
- Deliver well-tested, maintainable, and performant code ready for production deployment.
Other
- Ability to work effectively in cross-functional teams and take feedback constructively.
- Full ownership of the projects you work on.
- Team of passionate people who love what they do.
- Exciting projects, ability to implement your own ideas and improvements.
- Opportunity to learn and grow.
