Senior AI engineer

AllysAI | AI-Native Enterprise; Abu Dhabi; Hybrid; AED 320.000 - 520.000; Vollzeit

Benefits dieser Stelle

UAE visa

Health insurance

Flexible time off

Ownership of live systems

Zusammenfassung

AllysAI in the UAE is seeking a Senior AI Engineer to own AI systems end-to-end, from design to production, and to lead engineers who build them, while working closely with client technical teams. This hands-on role focuses on building and shipping, with on-site engagements and a hybrid work model across Dubai/Abu Dhabi.

You will collaborate on regulated data projects in banking, pharma and government, ensuring guardrails and robust deployment.

Qualifikationen

• 6+ years of software engineering, with 2+ years in production AI/LLM systems.
• Strong Python experience (FastAPI or similar) and API/data/deployment knowledge.
• Hands-on with vector search and re-ranking tools.
• Experience with Azure OpenAI or similar cloud AI services is a plus.
• Docker, CI/CD and production monitoring.
• Experience in regulated environments (banking, healthcare, government).
• Fluent English; Arabic or French is a plus.

Aufgaben

• Build production RAG pipelines with chunking, retrieval, re-ranking and citations.
• Develop agents and tool calling including MCP.
• Design evaluation guardrails: test sets, hallucination checks, red-teaming and safe handling.
• Create document AI pipelines: OCR, extraction and classification.
• Operate LLMs in production: model choice, monitoring, cost, latency and reliability.
• Work with sensitive regulated data under strict security policies.
• Review code, set engineering standards and guide the team.

Kenntnisse

Senior software Eng

Python (FastAPI)

Vector search

Azure

Cloud (AWS/GCP)

Docker

CI/CD

Regulated domains

Client communication

UAE-based

Tools

Azure OpenAI

Azure AI Search

Qdrant

pgvector

Jobbeschreibung

Senior AI Engineer – Production LLM Systems

AllysAI · UAE (Dubai / Abu Dhabi) · Full-time · Hybrid, with on-site client work

About AllysAI

AllysAI rebuilds enterprise operations as AI-native systems. We ship production AI like products, on our AllysOS platform, for organisations in regulated industries: banking, pharmaceuticals, government and energy. We’re headquartered in Abu Dhabi, with offices in New York and Lausanne.

The role

You’ll own AI systems end to end, from design to production, and lead the engineers who build them with you. This is a hands-on role, and most of your time goes into building and shipping. You’ll also work directly with client technical teams, and you’ll need to explain and defend your design in the room.

What you’ll do

• Build production RAG: chunking, retrieval, re-ranking, citations, and answers grounded only in approved sources
• Build agents and tool calling, including MCP
• Design evaluation and guardrails: test sets, hallucination checks, red-teaming and safe handling of regulated content
• Build document AI pipelines: OCR, extraction and classification
• Run LLMs in production: model choice, monitoring, cost, latency and reliability
• Work with sensitive banking, pharma and government data under strict security and data-protection rules
• Review code, set engineering standards and guide the team

What you bring

• 6+ years of software engineering, including at least 2 years building LLM or generative AI systems that run in production with real users
• Strong Python (FastAPI or similar), and comfort across APIs, data and deployment
• Hands-on experience with vector search and re-ranking (for example Azure AI Search, pgvector or Qdrant)
• Azure experience (Azure OpenAI, AI Search, Document Intelligence, API Management) is a strong plus; AWS or GCP is also welcome
• Docker, CI/CD and production monitoring
• Experience in regulated environments such as banking, healthcare or government
• Clear, confident English with clients; Arabic or French is a plus
• Based in the UAE, or ready to relocate

What we offer

• Competitive salary based on experience
• UAE employment visa and health insurance
• Flexible time off
• Real ownership: your systems go live at enterprise clients, not in demos