Junior AI Engineer

mindX360; Dubai; On-site; AED 210,000 - 360,000; Full time

Job summary

Emaar Group is seeking a frontend-like AI/ML engineering role to design, build, and ship production-grade, LLM-powered agentic applications across the enterprise. You will drive multi-agent orchestration, tool-calling loops, and code-execution sandboxes, built on frameworks such as Claude Agent SDK, with a focus on reliable, secure deployments.

You will own end-to-end data paths, including ingestion, embeddings, vector stores, and evaluation, and partner with business stakeholders to deliver

Qualifications

• Strong Python and systems engineering background with production-grade software experience.
• Hands-on LLM and agent experience—orchestration, RAG, evals, and prompt engineering.
• Experience with data pipelines, embeddings, vector stores, and production AI operations.
• Comfort with containerization (Docker) and CI/CD-based deployment of AI workloads.
• Ability to work across ambiguities and communicate outcomes to non-technical stakeholders.

Responsibilities

• Design and ship LLM-powered agentic applications with multi-agent orchestration and tool-calling loops.
• Architect RAG pipelines over enterprise data, including retrieval, context, and guardrails.
• Own full data path: ingestion, embeddings, vector stores, evaluation.
• Engineer prompts, context strategies, and agent memory for robust orchestration.
• Build evaluation harnesses and production dashboards for insights.

Skills

Python

LLM engineering

Data pipelines

CI/CD

Docker

Multi-agent orchestration

Stakeholder communication

Education

Bachelor’s degree in CS/AI/Data Science/Engineering

Tools

Docker

Kubernetes

Claude Agent SDK

Job description

The role holder is responsible for designing, building, and shipping production-grade, LLM-powered agentic applications across Emaar Group, covering multi-agent orchestration, tool-calling workflows, code-execution sandboxes, and retrieval-augmented generation (RAG) over enterprise data. The role holder takes ambiguous business problems and turns them into reliable intelligent systems engineering the retrieval, context, and guardrail layers that make agents dependable, and packaging solutions for production through containerization and CI/CD. This includes owning the full data path (ingestion, embeddings, vector stores, and evaluation), operating AI systems in production, and partnering with business stakeholders to drive real go-lives that deliver measurable business value.

Managerial Responsibilities

• Contribute to the strategic roadmap for AI and agentic systems in line with Emaar’s digital and operational transformation goals.
• Establish engineering standards, evaluation frameworks, and guardrails for LLM applications, ensuring reliability, safety, and responsible AI practices.
• Monitor and optimize AI platform consumption (model, token, and infrastructure costs) to ensure cost-effective scaling of AI workloads.
• Define and track KPIs for agent performance, output quality, system reliability, and business adoption of AI solutions.
• Act as the primary technical escalation point for production AI system issues and high-impact incidents.

Core Responsibilities

• Design and ship LLM-powered agentic applications — multi-agent orchestration, tool-calling loops, and code-execution sandboxes — built on frameworks such as the Claude Agent SDK.
• Architect and implement RAG pipelines over messy, real-world enterprise data, engineering the retrieval, context, and guardrail layers that make agents reliable.
• Own the full data path for AI solutions, including ingestion, embeddings, vector stores, and evaluation.
• Engineer prompt and context strategies, agent memory, and orchestration logic that go well beyond simple API calls.
• Build evaluation harnesses (automated evals, regression checks, and human-in-the-loop review) to measure and continuously improve agent quality and reliability.
• Build and maintain ETL/data pipelines and production dashboards, transforming complex enterprise data into reliable, actionable insights for technical and business stakeholders.
• Package and deploy solutions for production using Docker and CI/CD, with monitoring, logging, and observability for AI workloads.
• Integrate agentic solutions securely with enterprise platforms and data sources, ensuring access control and data governance compliance.
• Research unsolved problems independently, architect agentic systems for them, ground them in real data, and take them to production.
• Partner with business stakeholders to scope use cases, iterate rapidly, and drive real production go-lives rather than proof-of-concept demos.
• Work confidently in messy or evolving codebases, refactoring and hardening systems so they ship and remain stable in production.
• Own the end-to-end software engineering lifecycle, from requirements gathering, design, development, testing, and code review through deployment, monitoring, and ongoing maintenance.
• Partner with PMO to ensure timely delivery of AI initiatives with clear scope, milestones, and risk mitigation.

People Management Responsibilities

• Mentor engineers, analysts, and vendor resources on agentic AI patterns, prompt and context engineering, and production AI practices.
• Champion an ownership-driven engineering culture — self-directing work, sharing knowledge, and raising the technical bar of the team.
• Promote AI literacy and responsible AI awareness across IT and business teams.
• Coordinate onboarding and knowledge transfer across service providers and internal resources to ensure continuity of AI solutions.

Key Internal Interactions

• Business Units: Finance, Procurement, HR, Legal, Commercial, Malls, Entertainment, Hospitality, Properties, Digital & Operations
• PMO and Transformation Office
• Cybersecurity, Data Governance & Compliance
• Enterprise Applications, Infrastructure, and Integration Architecture Teams

Key External Interactions

• AI Platform and Model Providers (Anthropic, OpenAI, Microsoft, Google, AWS, etc.)
• Implementation & Integration Partners
• Managed Service Providers (MSPs)
• External Auditors and Regulatory Authorities

Minimum Qualifications

Bachelor’s degree in Computer Science, Artificial Intelligence, Data Science, Engineering, or a related field.

Professional Certifications (Preferred)

• Cloud AI/ML certifications (Azure AI Engineer, AWS Machine Learning Specialty, Google Cloud ML Engineer)
• Docker / Kubernetes certifications (DCA / CKA)
• Responsible AI / AI governance credentials (e.g., ISO/IEC 42001, NIST AI RMF)

Language Skills

Written and spoken English is essential, Arabic is preferred.

EXPERIENCE

0–3 years of software / systems engineering experience.

Nature of Experience

• Strong Python and systems engineering background, with a proven record of shipping production-grade software end to end.
• Hands-on LLM and agent experience - orchestration, RAG, evals, and prompt and context engineering -- not just API calls.
• Experience with data pipelines, embeddings, vector stores, and production AI operations (monitoring, reliability, cost control).
• Comfort with containerization (Docker) and CI/CD-based deployment of AI workloads.
• Demonstrated ability to self-direct research on ambiguous problems and communicate outcomes clearly to non-technical stakeholders.
• Experience building ETL/data pipelines and production dashboards, transforming complex datasets into reliable, actionable insights for technical and business stakeholders.
• Strong understanding of the end-to-end software engineering lifecycle, from requirements, design, development, testing, and code review through deployment, monitoring, and ongoing maintenance.

Proficiency Level

• Fast Pace & Resilience
• Achieving results under pressure
• Customer & Stakeholder Management
• Proactive & initiative driven
• Problem Solving

Technical Competencies

• Agentic AI & LLM Engineering (Orchestration, RAG, Evals)
• Python & Systems Engineering
• Data Pipelines, Embeddings & Vector Stores
• AI Ops, Docker & CI/CD
• Research, Problem Solving & Stakeholder Communication