linkedin
Agentic AI Systems Architect / Developer
Araby.AI
Abu Dhabi Emirate, UAE
Internship
Senior
Today
LangGraphLangChainCrewAIAutoGenSemantic KernelNode.js
Free
Job Fit Check
Base Career helps you apply smarter for this job.
?%
Ready to ScanKey skills for this role
LangGraphLangChainCrewAI
About the Role
Araby.AI seeks an Agentic AI Systems Architect to design and build production-grade AI systems with multi-step planning, tool calling, and enterprise integrations. Requires hands-on experience with agentic frameworks, advanced RAG, and Node.
Key Skills for This Role
LangGraphLangChainCrewAIAutoGenSemantic KernelNode.js
Responsibilities
- Design and build production grade AI systems beyond basic chatbots or simple RAG implementations
- Architect systems where AI agents can plan and reason through multi step tasks
- Enable agents to retrieve and validate information
- Implement safe tool/function calls
- Work with memory, state, and user context
- Integrate with APIs, databases, and internal systems
- Operate in secure enterprise or government environments
Requirements
- Hands on experience with agentic AI frameworks such as LangGraph, LangChain, CrewAI, AutoGen, Semantic Kernel, or custom orchestration layers
- Experience with agent loops, planning/execution flows, task decomposition, reflection, validation, and human in the loop workflows
- Experience with tool calling / function calling, structured outputs, JSON schemas, API execution, and tool safety controls
- Experience with stateful AI workflows including state machines, graph based orchestration, session state, and workflow persistence
- Experience with advanced RAG pipelines including chunking, embedding selection, hybrid search, metadata filtering, query rewriting, reranking, context compression, retrieval evaluation, and hallucination mitigation
- Experience with memory architecture (short term, long term, user specific, vector memory, persistent knowledge stores)
- Experience with LLM guardrails including prompt injection protection, permission aware retrieval, output validation, policy checks, tool execution safety, and response verification
- Experience with LLM observability and evaluation including tracing, prompt/version management, eval datasets, regression testing, latency analysis, cost monitoring, and failure analysis
- Experience with enterprise integrations including REST APIs, databases, CRMs/ERPs, document stores, webhooks, queues, and workflow engines
- Experience with vector databases such as Qdrant, Weaviate, Pinecone, Milvus, Chroma, pgvector, Elasticsearch, or OpenSearch
- Experience with secure deployment architectures for private cloud, on premise, offline, or government secure environments
- Basic knowledge of Node.js for API integration, backend connectivity, and service orchestration
Full Job Posting
Role Overview
- We are looking for an Agentic AI Systems Architect who can design and build production grade AI systems beyond basic chatbots or simple RAG implementations.
- The ideal candidate should understand how to architect systems where AI agents can plan, reason, retrieve, validate, execute tool calls, work with memory, interact with APIs, and operate in secure environments.
Technical Requirements
- Hands on experience with agentic AI frameworks such as LangGraph, LangChain, CrewAI, AutoGen, Semantic Kernel, or custom orchestration layers.
- Experience with agent loops, planning/execution flows, task decomposition, reflection, validation, and human in the loop workflows.
- Experience with tool calling / function calling, structured outputs, JSON schemas, API execution, and tool safety controls.
- Experience with stateful AI workflows including state machines, graph based orchestration, session state, and workflow persistence.
- Experience with advanced RAG pipelines including chunking strategies, embedding model selection, hybrid search, metadata filtering, query rewriting, reranking, context compression, retrieval evaluation, and hallucination mitigation.
- Experience with memory architecture including short term, long term, user specific, vector memory, and persistent knowledge stores.
- Experience with LLM guardrails including prompt injection protection, permission aware retrieval, output validation, policy checks, tool execution safety, and response verification.
- Experience with LLM observability and evaluation including tracing, prompt/version management, eval datasets, regression testing, latency analysis, cost monitoring, and failure analysis.
- Experience with enterprise integrations including REST APIs, databases, CRMs/ERPs, document stores, webhooks, queues, and workflow engines.
- Experience with vector databases such as Qdrant, Weaviate, Pinecone, Milvus, Chroma, pgvector, Elasticsearch, or OpenSearch.
- Experience with secure deployment architectures for private cloud, on premise, offline, or government secure environments.
- Basic knowledge of Node.js for API integration, backend connectivity, and service orchestration.
Apply for this job in 1 click
Skip the repetitive application forms
Install the Base Career Chrome Extension and autofill job applications across major job boards with your profile.
Trusted by over 500,000 job seekers on Base Career