Zendesk’s people have one goal in mind: to make Customer Experience better. Our products help more than 125,000 global brands (AirBnb, Uber, JetBrains, Slack, among others) make their billions of customers happy, every day.
The AI/ML Platform team is at the forefront of this mission. We build the foundation that powers every AI-driven experience at Zendesk, enabling product teams to build, evaluate, and deploy state-of-the-art Large Language Model (LLM) applications reliably and at scale.
We’re looking for a Prompt Engineer at the ML Engineer II level to design, test, and optimize the prompts, system messages, and evaluation strategies that power Zendesk’s GenAI features. You’ll work closely with applied ML teams, product managers, and researchers to ensure LLM outputs are accurate, safe, and aligned with product goals.
This is a hands-on, experimentation-heavy role, perfect for someone who blends strong ML engineering skills with deep curiosity about language models and a passion for improving AI output quality.
What you get to do every day
Create and refine prompts, system messages, and instructions for a variety of LLM-powered Zendesk products.
Work with ML engineers to design automated and human-in-the-loop evaluation pipelines for prompt performance, accuracy, and safety.
Run structured experiments to compare prompts, parameter settings, and model variants, using A/B testing and offline benchmarks.
Adapt prompts for multiple LLM providers (OpenAI, Anthropic, Google, Llama) while maintaining consistency in behavior.
Maintain prompt libraries, guidelines, and best practices to accelerate development across teams.
What you bring to the role
2–4 years of ML, NLP, or software engineering experience, with exposure to production-grade AI systems.
Understanding of how prompts, temperature, system instructions, and context windows impact LLM behavior.
Experience designing or running experiments to assess model output quality, accuracy, and safety.
Proficiency in Python, with experience in data analysis, scripting, and working with APIs.
Ability to identify failure cases, debug prompt behavior, and iterate quickly.
Ability to work effectively in cross-functional teams and take feedback constructively.
Experience with prompt engineering or prompt chaining for LLMs.
Knowledge of few-shot and zero-shot prompt design.
Familiarity with vector databases, retrieval-augmented generation (RAG), and grounding techniques.
Exposure to agentic frameworks such as LangChain, Haystack, or semantic workflow engines.
What our tech stack looks like
Our code is written in Python.
Our servers live in AWS.
LLM Vendors: OpenAI, Anthropic, Google, Llama
Infra: Kubernetes, Docker, Kafka, AWS
What we offer
Full ownership of the projects you work on.
What you will be doing will have a huge impact.
Team of passionate people who love what they do.
Exciting projects, ability to implement your own ideas and improvements.
Opportunity to learn and grow.
...and everything you need to be effective and maintain work-life balance
Flexible working hours.
Professional development funds.
Comfortable office and a remote setup.
Choice of your laptop and other equipment.
Premium Medical Insurance as well as Private Life Assurance.
Hybrid: In this role, our hybrid experience is designed at the team level to give you a rich onsite experience packed with connection, collaboration, learning, and celebration - while also giving you flexibility to work remotely for part of the week. This role must attend our local office for part of the week. The specific in-office schedule is to be determined by the hiring manager.
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.
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 [email protected] with your specific accommodation request.
