About The Role
We're hiring an Expert Prompt Engineer to shape the intelligence layer of our vertical AI systems. In this role, you'll design and optimize high-quality prompts for large language models (LLMs), automate their evaluation, and build tools to version, track, and scale them in production.
You'll work at the intersection of prompt engineering, LLMOps, and multi-agent orchestration; crafting the brains behind our AI agents that serve real-time restaurant operations across the US.
If you treat prompt design like programming, and know how to evaluate prompts at scale, this is for you.
What will be your responsibilities?
- Design and refine prompts for GPT, Claude, LLaMA, and other frontier LLMs.
- Build structured prompt chains for agentic workflows, retrieval, summarization, classification, and reasoning.
- Implement automated evaluation pipelines to test prompt quality, accuracy, latency, and safety.
- Manage prompt versioning with reproducible metadata and performance diffing.
- Harden prompts against injection, hallucination, and failure cases using safety guardrails and fallback flows.
- Collaborate with product, MLOps, and backend teams to integrate prompts in full-stack AI systems.
- Conduct A/B testing and experiments using tools like LangSmith, TruLens, or custom eval harnesses.
- Optimize prompt cost vs. output quality tradeoffs.
- Create libraries and templates for reusable, scalable prompt patterns across use cases.
What are we looking for and what does it require to be the right fit for this role?
- 2+ years of hands-on experience with LLMs (OpenAI, Claude, LLaMA, etc.).
- Deep expertise in few-shot, zero-shot, chain-of-thought, ReACT, and tool-calling prompt patterns.
- Experience with LLMOps tools such as LangChain, LangSmith, PromptLayer, Ragas, or TruLens.
- Proficient in writing structured outputs (e.g., JSON prompts) and using parsing tools (Pydantic, schema validators).
- Familiar with safety techniques like guardrails, moderation APIs, and injection prevention.
- Strong understanding of token efficiency, temperature tuning, and prompt testing.
- Experience in multi-agent architectures or agent frameworks (CrewAI, AutoGen, DSPy) is a plus.
- Bonus: Experience with RAG pipelines, vector DBs, or AI in vertical SaaS.
If you can prompt anything to do everything—this is your place.
Why Join AIO?
Our mission is to revolutionize the US restaurant industry by providing a comprehensive and fully integrated solution that empowers restaurant owners to efficiently manage all aspects of their businesses. Our platform, designed to meet the unique challenges (post COVID-19) faced by restaurants, combines our patented AI technology with unparalleled customer support to help owners increase revenue, reduce costs, and improve their overall profit margins.
We believe that restaurants should be able to focus on delivering exceptional dining experiences to their customers, without the added stress of managing complex and disparate systems. That's why we offer an All-In-One super app platform for all of their needs, from front-of-the-house operations like ordering, payment, marketing and rewards, to back-of-the-house management like inventory, staff, and financials.
We are laser focused to become a significant player in the $55 billion restaurant tech SaaS market. You will be a part of a world class silicon valley funded startup.