AI Automation Engineer / Architect of Agentic AI (Automator)

01. About The Company

About The Role

03. Who You Are

• **LLM Engineer**
• You understand how language models actually work — tokenisation, logits, prompting, and system behaviour.
• **Agent Systems Builder**
• You’ve worked with or built multi-agent systems and understand orchestration, roles, and control flows.
• **Automation Thinker**
• You design systems that take action — not just generate outputs.You can wrap agents into APIs, manage integrations, and handle async workflows.You understand access control, permissions, and how to prevent unsafe behaviour in agent systems.04.

Responsibilities

• **Backend Engineer**
• **Security-Aware**
• **Prompt Engineering & System Design**
• Design structured, multi-layered prompt systems with context management, self-correction, and reliability controls.
• **AI Hub Development**
• Build and configure internal AI systems (Claude, GPT, open-source models) connected to company data, tools, and APIs.
• **Multi-Agent Architecture**
• Design and implement hierarchical agent systems (orchestrators, specialised agents, execution layers) with clear responsibilities and control flows.Integrate AI agents with internal systems — CRM, databases, messaging platforms, CI/CD — enabling real actions and workflows.Build and maintain tools that allow agents to interact with external systems (APIs, services, internal infrastructure).05.

Requirements

• **Integration & Automation**
• **Tooling & Execution**
• Strong understanding of LLM internals (tokenisation, logits, temperature, system prompts, RAG).
• Experience building or working with agent frameworks (LangChain, LangGraph, AutoGen, CrewAI, or custom systems).
• Strong backend experience (Python or TypeScript).
• Experience building APIs, handling async workflows, and integrating external systems.
• Experience implementing function calling, tools, and agent execution workflows.
• Understanding of prompt security, injection risks, and hallucination control.
• Experience integrating AI systems into real business processes or products.

06. Nice To Have

• Experience building multi-agent systems in production.
• Experience integrating agents with CRM, databases, or CI/CD pipelines.
• Experience with Model Context Protocol (MCP) or similar tooling approaches.
• Experience working in fast-paced or AI-first environments.

07. What We Offer

• Real ownership and direct impact on a global AI infrastructure product
• Fast execution, low bureaucracy, and a highly collaborative, idea-driven team
• Exposure to cutting-edge AI, distributed systems, and hardware-level optimization
• Competitive salary with performance-based incentives
• 24 days annual leave, plus public holidays
• Health insurance
• Modern office in Yas Creative Hub
• Continuous learning through real-world problem solving — not just theory
• The opportunity to shape what you're working on and influence product direction
• A diverse, open-minded team where ideas are genuinely heard
• 08.

How To Apply

• As part of your application, please share:
• A diagram or description of a multi-agent system you've built (or would build).
• An example of a complex prompt using tools/function calling.
• Your approach to enforcing access control across agent systems.

Application Question(s)

• Do you understand tokenization, logits, temperature, and their effect on LLM output behavior?
• Have you ever implemented a Retrieval-Augmented Generation (RAG) pipeline from scratch (not using a managed service)?
• On a scale of 1–5, how confident are you in building prompts resistant to injection attacks? (1 \= not confident, 5 \= expert)
• Rate your understanding of API authentication methods (OAuth, API keys, JWT)? (1 \= vague, 5 \= expert)
• Have you built a self-correcting prompt with an automated feedback loop?
• Number of years of professional experience in LLM engineering (0, 1, 2, 3, 4, 5+).
• Is your portfolio submission complete with all three requested items (diagram, complex prompt, access control thoughts)?
• Have you built or deployed a multi-agent system (not just single-agent chatbots)?
• Have you implemented function calling (tools) where an agent executes external APIs autonomously?
• Number of production LLM automation projects you have shipped? (0, 1–2, 3–5, 6-8, 10+)
• Have you integrated LLM agents with CRM, database, or CI/CD pipelines?
• Can you build an API wrapper around an agent that handles async webhooks?
• Rate your Python proficiency (1 \= basic, 5 \= architect-level)
• Rate your TypeScript proficiency (1 \= basic, 5 \= architect-level)