AI Systems Architect & Developer

We are looking for an Agentic AI Developer who can design, build, and optimize advanced AI systems that go beyond simple chatbot or basic RAG implementations. The ideal candidate should have hands-on experience creating multi-agent workflows, tool-using AI agents, retrieval systems, reasoning pipelines, orchestration layers, and production-ready AI architectures.

This role requires someone who understands how to build complex AI systems where multiple components work together, including LLMs, vector databases, APIs, memory, tools, workflows, permissions, guardrails, and backend services. The candidate should be able to think architecturally, break down business problems into AI workflows, and design systems that are scalable, secure, reliable, and suitable for enterprise or government environments.

The candidate should also have basic to intermediate knowledge of Node.js, enough to connect AI services with backend APIs, build lightweight services, integrate third-party tools, and support implementation with the engineering team.

Technical Requirements

The candidate should have hands-on experience with:

• Agentic AI frameworks such as LangGraph, LangChain, CrewAI, AutoGen, Semantic Kernel, or custom orchestration layers
• Agent loops, planning/execution flows, task decomposition, reflection, validation, and human-in-the-loop workflows
• Tool calling / function calling, structured outputs, JSON schemas, API execution, and tool safety controls
• Stateful AI workflows, including state machines, graph-based orchestration, session state, and workflow persistence
• Advanced RAG pipelines, including:
• Chunking strategies
• Embedding model selection
• Hybrid search
• Metadata filtering
• Query rewriting
• Reranking
• Context compression
• Retrieval evaluation
• Hallucination mitigation
• Memory architecture, including:
• Short-term memory
• Long-term memory
• User-specific memory
• Vector memory
• Persistent knowledge stores
• LLM guardrails, including:
• Prompt injection protection
• Permission-aware retrieval
• Output validation
• Policy checks
• Tool execution safety
• Response verification
• LLM observability and evaluation, including:
• Tracing
• Prompt/version management
• Eval datasets
• Regression testing
• Latency analysis
• Cost monitoring
• Failure analysis
• Enterprise integrations, including REST APIs, databases, CRMs/ERPs, document stores, webhooks, queues, and workflow engines
• Vector databases such as Qdrant, Weaviate, Pinecone, Milvus, Chroma, pgvector, Elasticsearch, or OpenSearch
• Secure deployment architectures for private cloud, on-premise, offline, or government-secure environments
• Node.js basics, including API development, async workflows, service integration, and connecting AI systems to backend applications

Important Note

This role is not for someone who has only built a basic chatbot or RAG over a few PDFs.

We are looking for someone who can architect real agentic AI systems with:

• Agents
• Tools
• Memory
• Retrieval
• Validation
• Orchestration
• Security
• Monitoring
• Production deployment

Work location:

Abu Dhabi - in office

Job Type: Full-time

Pay: AED10,000.00 - AED11,000.00 per month

Application Question(s):

• What is the difference between a basic RAG chatbot and an agentic AI system?
• ⁠How would you handle user permissions when the agent retrieves documents from multiple departments?
• How would you evaluate and audit an agent’s decisions, tool calls, and retrieved sources in production?

Experience:

• AI Agent & Routing Engineer: 2 years (Required)

Language:

• English (Required)

Work Location: In person