Technical Principal Engineer (AI Platform)

Our client is the next-generation digital real estate platform in the UAE that streamlines and manages the full property lifecycle. The platform combines AI capabilities with traditional tools, enabling structured management of properties, tenants, and processes with full control and visibility when needed.

About the Role
This is a hands-on technical leadership role at the core of the company’s product and engineering direction. You will architect both a next-generation SaaS platform and an internal AI-first engineering system that defines how it is built, tested, and scaled.

You will design and operate an internal development platform powered by AI agents—including orchestration, task decomposition, evaluation systems, and CI/CD integration—enabling a small senior team to deliver at high velocity and enterprise-grade quality. A key part of the role is defining what is executed by humans versus AI agents.

Responsibilities:

AI-First Engineering System

• Design and operate the AI engineering platform (orchestrator, agent coordination, review gates, deployment and rollback flows)
• Build and manage a fleet of coding, testing, review, and operations agents
• Establish a spec-driven development model translating product intent into machine-executable workflows
• Define governance, autonomy boundaries, and verification layers (tests, evals, tracing, canary releases)
• Continuously improve system performance, autonomy, cost efficiency, and reliability across the SDLC

Product & Technical Architecture

• Own end-to-end SaaS architecture (services, APIs, data models, infrastructure)
• Make fast, high-impact architectural decisions in a startup environment
• Define and implement AI as a core product layer, not a feature
• Design real-time systems including dashboards and event-driven pipelines

Hands-On Engineering

• Build production-grade systems directly and alongside AI agents
• Own frontend, backend, database design, and performance optimization
• Deliver scalable, reliable code across the full stack

AI / LLM Layer

• Own the full AI stack from prototype to production
• Build and maintain RAG pipelines, vector databases, and LLM integrations
• Design prompt strategies and AI workflows for core use cases
• Evaluate and integrate emerging AI capabilities into production systems

Integration Layer

• Own integrations across external systems (IoT, smart locks, payments, government and regulatory APIs)
• Ensure integrations are reliable, observable, and scalable for future expansion

Engineering Leadership & Delivery

• Lead a small high-performance hybrid team (engineers + AI agents)
• Set engineering standards, run reviews, and ensure delivery under pressure
• Translate product requirements into structured, agent-executable work
• Build and drive an AI-native engineering culture

Infrastructure & Reliability

• Own cloud infrastructure, CI/CD pipelines, and deployment architecture
• Implement observability across systems: monitoring, alerting, tracing, cost and latency tracking
• Ensure production readiness, reliability, and operational transparency

Requirements

• 5–7+ years of software engineering experience, including hands-on technical leadership of engineering teams
• Proven 0 → 1 experience building systems, teams, and architecture from scratch (not within already scaled organizations)
• Strong backend engineering expertise (TypeScript / Node.js or equivalent), with ability to design and evolve scalable service architectures
• Solid frontend capability (React, Vue.js or equivalent), with ability to architect, review, and unblock teams when required
• Deep understanding of data architecture (PostgreSQL or equivalent), including multi-tenant systems, performance optimization, and access control models
• Ability to define, select, and evolve technology stacks based on product needs and constraints, not industry trends
• Full-stack capability when needed, with strong architectural judgment and clear trade-off decision-making
• Daily, production-grade use of agentic coding tools across real systems (not demos or experimental use cases)
• Proven experience shipping features where a significant portion of production code is AI/agent-authored under your direction
• Hands-on experience designing or significantly extending AI-driven engineering workflows, including multi-agent orchestration, spec-to-PR pipelines, automated review systems, or agent-based testing frameworks
• Production experience integrating LLM-based systems into user-facing products, including RAG pipelines, vector databases, prompt engineering, and evaluation frameworks