Senior Solo AI Engineer (Python, Airgapped, Conversational and Voice AI)

About the role

We are looking for a senior AI engineer to design and deliver Arabic and English chat and voice assistants for UAE government services. The role spans cloud‑based and fully air‑gapped environments, requiring end‑to‑end ownership from requirements to live support.

Key responsibilities

• Develop multi‑step chat journeys with intent detection, tool calling, and transaction handling for services such as traffic fines, licence renewals and payments.
• Implement streaming speech recognition and synthesis, barge‑in, and seamless hand‑off between voice and visual UI.
• Build and maintain Retrieval‑Augmented Generation pipelines that ingest bilingual PDFs, DOCX and scanned documents, provide citations and evaluate relevance.
• Deploy and optimise LLM serving both via hosted APIs and locally on GPU servers using vLLM, TensorRT‑LLM, quantisation and latency tuning.
• Integrate with SOAP/WSDL, REST, UAE PASS, OAuth and payment gateways, ensuring idempotent, auditable transactions.

Required profile

• 4+ years of production Python experience, including async services, APIs and background workers.
• Proven delivery of LLM‑based applications (RAG, tool‑calling or agents) in production.
• Strong Linux skills: containers, networking, TLS, debugging in air‑gapped environments.
• Ability to work independently, own the full delivery cycle and communicate concise progress updates.
• Based in the UAE or able to relocate quickly; on‑site presence required.

Required skills

• Python
• Async services, APIs, background workers
• LLM, RAG, tool calling, vLLM, TensorRT‑LLM
• GPU serving, quantisation, latency tuning
• Linux, containers, systemd, TLS, networking
• SOAP 1.1/1.2, WSDL, XML, REST
• UAE PASS, OAuth, payment gateway integrations
• SQL Server or comparable enterprise databases