Conversation AI Engineer

Atribs Metscon Group; Abu Dhabi; On-site; AED 180,000 - 240,000; Full time

Job summary

Atribs Metscon Group is seeking an experienced software engineer to build bilingual AI agents for a major UAE energy client. You will develop and deploy retrieval-driven assistants that operate in English and Arabic, with production-ready quality controls and security compliance.

You will design conversational flows, implement language detection and Arabic responses suited to Gulf users, and collaborate with client teams to ensure seamless handover and training for ongoing operation.

Qualifications

• Three years or more building software, with at least one year on LLM based applications that reached real users.
• Production experience with retrieval over enterprise content and a view on why retrieval quality fails.
• Strong Python, and comfortable in someone else’s codebase and cloud account.
• Experience designing conversation flows, including failure paths as well as ideal paths.
• Evidence of measuring an AI system rather than just demonstrating it.
• Able to work onsite with client teams and explain technical decisions to non-technical stakeholders.

Responsibilities

• Design and build AI agents that resolve customer enquiries from approved knowledge sources, with answers traceable to source content.
• Own retrieval quality: content preparation, chunking, indexing, refreshing, and agent behavior when no good answer exists.
• Build and tune bilingual behaviour, including language detection and switching mid-conversation, and Arabic responses suitable for a Gulf audience.
• Define escalation rules and handover to human agents to avoid loops.
• Set up evaluation before launch: test sets, accuracy measurement, regression checks on changes.
• Instrument the agent so client-visible metrics like resolution rate and escalation volume are tracked.
• Work in the client environment under their security and data residency requirements.
• Hand over documentation and run training so the client’s team can operate and extend the agent.

Skills

Python

LLM applications

Conversation design

Retrieval augmentation

Cloud & security

Stakeholder comms

Job description

Job description

ABOUT

Enterprise AI and technology consultancy headquartered in Abu Dhabi, operatingacross the GCC, the United Kingdom and Germany. We deliver implementation ledengagements for regulated enterprise clients in banking, energy, healthcare andgovernment.

We aredeployment agnostic: sovereign air gapped, on premise, private cloud and publiccloud. We are hired to put working systems into production and to leave theclient able to run them.

PURPOSE OF THE ROLE

You buildcustomer facing AI agents that answer real enquiries correctly, in English andArabic, and you are accountable for how they behave in production. Our firstdeployment for this role is a bilingual customer service agent for a majorclient in the UAE energy sector, covering web, messaging and voice.

WHAT YOU WILL DO

• Design and build AI agents that resolve customerenquiries from approved knowledge sources, with answers traceable to sourcecontent
• Own retrieval quality: how content is prepared,chunked, indexed and refreshed, and how the agent behaves when it has no goodanswer
• Build and tune bilingual behaviour, including languagedetection, switching mid conversation, and Arabic responses that read naturallyto a Gulf audience
• Define escalation rules and the handover to humanagents, so the customer is never left in a loop
• Set up evaluation before launch: test sets, accuracymeasurement, regression checks on every change
• Instrument the agent so resolution rate, escalationvolume and response accuracy are visible to the client in reporting
• Work in the client's environment under their securityand data residency requirements
• Hand over documentation and run training so theclient's own team can operate and extend the agent

WHAT SUCCESS LOOKS LIKE IN THE FIRST 90 DAYS

• A working agent in a client environment, answering adefined enquiry set in both languages
• An evaluation set the client agrees represents theircustomers, with measured accuracy against it
• Escalation and handover rules signed off by theclient's service team

ESSENTIAL EXPERIENCE

• Three years or more building software, with at leastone year on LLM based applications that reached real users
• Production experience with retrieval over enterprisecontent, and a clear view on why retrieval quality fails
• Strong Python, and comfort working inside someoneelse's codebase and cloud account
• Experience designing conversation flows, includingfailure paths, not only the ideal path
• Evidence of measuring an AI system rather thandemonstrating it
• Able to work onsite with client teams and explaintechnical decisions to non technical stakeholders

DESIRABLE

• Arabic language skills, particularly Gulf dialecthandling in speech or text
• Experience with contact centre platforms, WhatsAppBusiness or voice channels
• Work in a regulated environment: banking, energy,healthcare or government
• Exposure to guardrails, prompt injection defence andcontent safety in customer facing systems