AI Architect

Theomnihire; Abu Dhabi; On-site; AED 350,000 - 520,000; Full time

Job summary

Theomnihire in the United Arab Emirates is seeking a senior AI/LLM product leader to design and deploy responsible AI features on Azure OpenAI in UAE regions. The role focuses on building a safeguarded AI gateway, enabling explainable suggestions, and ensuring high standards for data redaction and audit trails.

You will craft guardrails, evaluation methods, and a content pipeline to convert large slide decks into CMS-ready English and Arabic content, with human verification at each unit.

Qualifications

• 10+ years in software with leadership in AI/LLM product areas.
• Hands-on retrieval, prompt and tool design, evaluation, guardrails and cost control.
• Experience with Azure OpenAI and Azure platform in regulated settings.
• Knowledge of data residency and privacy obligations in UAE.

Responsibilities

• Design AI features on Azure OpenAI in UAE regions, including an AI CV builder with explanations.
• Set up and run AI gateway with data redaction and thorough request logging.
• Build safety for minors: boundaries, refusals, red-teaming and evaluation harness.
• Develop content pipeline turning hundreds of slides into CMS-ready English/Arabic content, with verification.
• Define delivery team usage of AI review tools and policy guardrails.
• Advise on governed citizen development for client staff in later phases.

Skills

LLM product design

Prompt design

Tool design

Evaluation guardrails

Azure OpenAI

Azure platform

Data privacy

Cost control

AI risk communication

Agentic coding tools

Tools

Claude Code

GitHub Copilot

Job description

Abu Dhabi, United Arab Emirates

WHAT YOU WILL DO

• Design the platform's AI features on Azure OpenAI in UAE regions: an AI CV builder that explains every suggestion it makes, and a guardrailed conversational assistant for young users, grounded in approved content.
• Set up and run the AI gateway: personal data redacted before model calls, every request logged with prompt, model, version and output, and system prompts kept under version control and shared with the client.
• Build safety for an audience that includes minors: topic boundaries, refusal behaviour , red-teaming, and an evaluation harness the client can rerun.
• Design the AI-assisted content pipeline that turns several hundred pages of source slides into structured, CMS-ready English and Arabic content, with a person verifying every unit.
• Define how the delivery team uses agentic coding and AI review tools: the AI usage policy, guardrails on prompts and source code, tagging of AI-assisted commits, and the quality gates they pass.
• Advise on governed citizen development (low-code and AI builders) for the client's own staff in later phases.

WHAT YOU BRING

• 10+ years in software, including 3+ years building LLM products in production.
• Hands-on retrieval, prompt and tool design, evaluation, guardrails and cost control.
• Azure OpenAI and the wider Azure platform (networking, Key Vault, monitoring) in regulated environments.
• Working knowledge of data residency and privacy obligations, ideally the UAE PDPL and government AI policies.
• Daily fluency with agentic coding tools such as Claude Code or GitHub Copilot, and a clear view of where they fail.
• The ability to explain AI risk and design trade-offs to senior, non-technical government stakeholders.

NICE TO HAVE

• Arabic language processing.
• Copilot Studio or Power Platform governance.