Arada | Senior AI Engineer, Dubai

Role purpose

Key responsibilities

• Architect production LLM applications, multi-agent systems, and RAG pipelines end to end.
• Choose models and providers, balancing cost, latency, and quality.
• Design context engineering for retrieval, tool use, memory, and grounding in project, inventory, pricing, and CRM data.
• Establish evaluation, red-teaming, and guardrail practices for safety, hallucination control, and factual grounding.
• Set architecture standards, conduct design reviews, and mentor AI Engineers across Dubai and offshore teams.
• Lead AI integrations with Salesforce, ERP, and the buyer/investor portal.
• Prototype agentic workflows, computer-use agents, and voice AI for real-estate use cases.
• Partner with Data and Platform teams on data and vector infrastructure.
• Present AI roadmap, risks, and ROI to leadership and participate in cross-functional planning.

Technology stack and AI skills

• Languages include Python and TypeScript/Node.js; backend options include FastAPI or Node/Express, with REST/GraphQL APIs.
• LLM providers and APIs include Anthropic Claude, OpenAI, and Azure OpenAI; orchestration includes LangChain, LangGraph, LlamaIndex, Anthropic Agent SDK, and MCP.
• Retrieval technologies include Pinecone, pgvector, Weaviate, or Azure AI Search, with hybrid BM25 and embedding search.
• Infrastructure includes Azure, Docker, Kubernetes/AKS, GitHub Actions/Azure DevOps, PostgreSQL, Azure Blob/Data Lake, and Airflow/ADF.
• Observability and evaluation tools include LangSmith, Langfuse, custom evaluation harnesses, and PromptFoo.
• AI practices include agent design, enterprise RAG, prompt/context engineering, structured outputs, tool calling, evaluation, red-teaming, safety guardrails, and cost/latency optimization.
• Fine-tuning/LoRA familiarity is useful; document/OCR pipelines and Salesforce and Dynamics 365 ERP APIs are integration targets.

Must-have requirements

• Strong software engineering background in Python and/or TypeScript/Node.
• Hands-on experience shipping LLM applications to production, not just prototypes.
• Deep understanding of RAG, embeddings, vector databases, and agent frameworks.
• Experience with major LLM provider APIs such as Anthropic, OpenAI, or equivalent.
• Solid system design, API design, and cloud infrastructure knowledge; Azure is preferred.
• Track record of technical leadership or mentoring.

Nice to have

• Experience with LLMOps tools for evaluations, observability, or guardrails.
• Real-estate, PropTech, or enterprise Salesforce/ERP integration experience.
• Familiarity with fine-tuning or model customization.
• Exposure to voice AI or computer-use/browser agents.

Business domain

Application process

• Candidates are asked to complete assessments and interviews independently without generative AI assistance.

About Arada