Description

We're hiring an AI agent designer to build, prompt-engineer, and continuously improve the AI agents that power OpenCX. You'll work directly with customers and our product team to translate real customer use cases into agent behavior that just works — designing conversation flows, writing and iterating on prompts, and measuring agent performance against real customer outcomes.

You'll develop deep expertise in the platform and the underlying LLMs we use, and partner with the product engineering team to push the boundaries of what our agents can do. Prompt engineering is the core of this role — you'll be writing, testing, and iterating on prompts daily, while constantly tuning agents based on real-world customer feedback.

The scope of agents you'll own and the depth of prompt iteration you'll drive will scale with your experience and ability to ship.

This is a hands-on AI/prompt engineering role with heavy customer exposure — not pure internal R&D, and not pure support.

What you'll do

• Design and build new AI agents end-to-end: define behavior, write the prompts, set up tool/function calls, and ship to customers.
• Iterate on prompts based on real customer conversations and edge cases — measuring quality, latency, and accuracy.
• Work directly with customers to understand their use cases, then translate them into agent behavior that just works.
• Run experiments across models, prompt structures, and agent architectures to push performance higher.
• Collaborate closely with the product engineering team: feed real customer needs back into platform improvements.
• Build deep expertise in our agent stack — LLMs, tools, evaluations — so you can advise customers on what's possible.
• Document agent design patterns, prompt templates, and evaluation playbooks to strengthen internal and customer resources.

Requirements

• Hands-on experience with prompt engineering and AI agents — you've built, tuned, and shipped LLM-powered features.
• Strong technical foundation — you can read code, work with APIs, and run evaluations to measure agent quality.
• Solid understanding of how modern LLMs behave, where they fail, and how to design prompts and tools to make them reliable.
• Customer-facing experience or strong willingness to engage directly with customers to learn their use cases.
• Excellent English communication skills — clear writing and confident speaking on video calls with enterprise stakeholders.
• Ability to operate effectively in a fast-moving startup: you prioritize speed, customer impact, and getting things done.
• Comfortable working remotely with customers across multiple global time zones.

Benefits

• Top of the market compensation
• Health insurance
• Working at a high-growth, YC-backed startup