About the role
In this role, you will take enterprise AI applications from technical design into dependable production use, owning the software, evaluations, and operational controls behind generative AI systems that work with customer data, tools, and business processes. Your work will involve applied AI engineering services including AI-native applications, enterprise retrieval-augmented generation (RAG), AI agents, document intelligence, and private AI deployment.
Ready to apply for roles like this?
Unlock the company name and direct application link. Subscribers get instant access to fresh jobs across Dubai, Abu Dhabi and Riyadh, many with visa support.
Unlock employer & apply directly
What you will do
- Design and implement Python services connecting large language models to enterprise APIs, data sources, and approved tools.
- Build retrieval-augmented generation systems, including document ingestion, indexing, retrieval, reranking, and source attribution.
- Engineer agentic workflows with explicit permissions, reliable state handling, retries, audit trails, and approval gates for consequential actions.
- Develop document intelligence pipelines that produce validated structured outputs for downstream applications and ERP workflows.
- Create evaluation datasets and release criteria; measure answer quality, failure modes, latency, and operating cost.
- Deploy and operate AI applications in customer-controlled cloud or private environments, with monitoring, incident handling, and clear handover documentation.
What you bring
- A record of delivering production software and LLM applications, with responsibility for architecture, deployment, and operational quality.
- Strong Python skills, API design, testing, and debugging, along with practical experience with containers, Git, and CI/CD.
- Hands-on experience with retrieval-augmented generation, tool use, structured outputs, and evaluation beyond prompt experimentation.
- Experience with Amazon Bedrock, Anthropic Claude, or comparable model services, and the ability to select models and deployment patterns for a use case.
- The ability to assess data access, untrusted inputs, and agent permissions, explain trade-offs to customers, and guide engineering decisions in English.
- Experience with self-hosted models, GPU infrastructure, vector search, MCP integrations, or agent frameworks is valuable. We welcome engineers who can explain when a simpler workflow is the better design.
What you can expect
You will work closely with the founders, own meaningful technical decisions, and shape how the team builds, evaluates, and operates enterprise AI. The work will involve both implementation and collaboration with customer engineering teams.
