AI Engineer

About Emplorium

Emplorium is a customer engagement platform that helps businesses handle sales, support, and customer conversations across their channels. Our AI agent, Aura, sits at the centre of the product and is deployed by teams to answer customer questions, qualify leads, and reduce response times. We operate in a competitive category alongside established customer service and conversational AI platforms, and we want to compete on product quality, usability, and the depth of the AI experience we deliver.

About the role

We are hiring our first Applied AI Engineer to lead the quality and capability of Aura. Aura today has the foundational pieces of a modern AI agent, knowledge sources, prompts, tools, channels, and analytics built on top of frontier LLMs. The next chapter of the product is about making Aura measurably more accurate, more grounded, and more trustworthy in production. That work has not yet been done, and it is the work we are hiring for.

This is a founding technical role for the AI function. You will not be training models; you will be building the layer around them: retrieval, context, tool use, and evaluation. That turns a capable general-purpose LLM into an agent that businesses can confidently deploy to their customers.

Responsibilities

• Design and improve Aura's retrieval and context pipeline: how customer knowledge is ingested, chunked, indexed, and selected at inference time.
• Own prompt and system design across the product, including agent personality, tool selection, and answer formatting.
• Design tool-use and function-calling patterns that let Aura safely query customer systems and take actions, with appropriate guardrails.
• Build and maintain an evaluation harness that measures answer quality, regression risk, and production behaviour, and use it to drive every change to the AI stack.
• Partner with product, design, and engineering to translate AI capability into features customers can understand and configure.
• Establish the technical direction for the AI function as the team grows.

Requirements

• Strong software engineering fundamentals (preferably in GO), with production experience shipping user-facing products.
• Demonstrated experience building on top of LLMs in production: retrieval-augmented generation, tool and function calling, and agent-style orchestration.
• A rigorous approach to evaluation. You build eval sets from real usage before making changes and can speak to how you have measured and improved LLM-powered systems in previous work.
• The judgement and independence to operate as the sole AI specialist on the team and set direction without close supervision.
• Clear written communication; comfort working across product and engineering functions in a remote environment.

Preferred

• Experience improving LLM quality for non-English languages, particularly Arabic and other MENA-market use cases.
• Familiarity with MCP, agent frameworks, and productionising LLM systems that connect to customer data sources.
• Prior experience at an early-stage company or as an early technical hire.

What we offer

• A founding technical role with direct ownership of the product's AI direction.
• Remote-first working, with a distributed team.
• Full-time or contract-to-hire arrangements considered for the right candidate.