Senior Software Engineer - AI Agents & GenAI

We are seeking a highly motivated, hands-on Senior Software Engineer (AI Agents & GenAI) to join an enterprise technology team in Dubai. Operating within the Software Engineering Chapter, this role focuses on designing, building, and deploying autonomous AI agent solutions, custom tools/skills, and microservices integrated with enterprise platforms (including Oracle Fusion HCM Cloud).The ideal candidate brings strong backend development experience in Node.js/TypeScript, deep expertise in LLM orchestration (LangChain/LangGraph), and practical skills in building reliable, multi-step agentic workflows and tool-calling mechanisms from ground up.RequirementsKey Responsibilities2. Prompt Engineering & Custom Tooling3. Backend Microservices & System Integration4. Testing, Monitoring & MaintenanceTechnical Specifications & Skills AI Agent Development & OrchestrationTranslate complex business requirements into working AI agent solutions using frameworks like LangChain, LangGraph, or Oracle AI Agent StudioDesign and execute multi-step agentic workflows (sequential, conditional, and parallel agent/tool calls, supervisor-worker patterns, and agent-to-agent handoffs)Implement advanced context management, model selection, caching, and guardrails to optimize for latency, cost, and hallucination reductionEstablish and manage workflow triggers across event-based, schedule-based (cron), webhook-based, and user-initiated execution flowsWrite and refine advanced prompt architecture (system prompts, role-based prompting, few-shot/zero-shot design, chain-of-thought structuring, structured JSON/XML outputs)Build and maintain custom tools, skills, and functions for agents to perform data lookups, calculations, document generation, and external action executionsProtect AI solutions against prompt injection attacks and handle edge-case failures gracefullyBuild and maintain scalable backend microservices using Node.js and TypeScriptIntegrate AI agents with internal and external REST/SOAP APIs, managing authentication (OAuth, SSO, API Keys), response parsing, retry mechanisms, and error handlingPerform database operations across relational and non-relational database storage layersSet up and manage version control (Git) and CI/CD pipelines for smooth agent and code deploymentThoroughly test agent behavior, evaluating non-deterministic outputs and edge cases systematicallySet up logging, tracing, and evaluation frameworks for production AI agent monitoring and debuggingMaintain clear architectural, API, and prompt documentation for long-term platform maintainabilityCore AI & LLM Stack (Essential)LLM Fundamentals: Solid grasp of tokens, temperature, top_p, streaming data, context windows, and non-deterministic logicPrompt Engineering & Tools: Expert in structured outputs, function/tool calling, guardrails, and advanced techniques (Chain-of-Thought, RAG / Vector Databases)Agentic Frameworks: Hands-on experience with LangChain, LangGraph, or similar agent frameworks; exposure to MCP (Model Context Protocol)API & Integration: Deep experience with REST/SOAP APIs, webhooks, and secure authentication (OAuth, SSO)Backend & Engineering Stack (Essential)Languages & Architecture: Strong proficiency in Node.js and TypeScript within a Microservices architectureDatabases & DevOps: Experience with Relational and NoSQL databases, Git version control, and CI/CD pipelinesPreferred / Added AdvantagesExperience with Oracle AI Agent Studio and Oracle Fusion HCM CloudExperience building multi-agent systems and supervisor/worker agentic patternsFamiliarity with AI monitoring, observability, and evaluation toolsQualifications & ExperienceEducation: Bachelor's or Master's degree in Computer Science, Software Engineering, Artificial Intelligence, or a related technical fieldExperience: 3-5 years of hands-on experience building LLM-based applications, AI agents, and backend services in production environmentsSoft Skills: Strong ownership mindset, analytical troubleshooting skills for AI systems, and excellent technical documentation capabilities