Lead AI Engineer, UAE

Job Summary

As a Lead AI Engineer, you will play a pivotal role in the design and implementation of a complex, agentic AI–based solution for a major B2C company in Dubai, a market leader in its sector.
The platform will deliver omni-channel, prompt-driven AI services, leveraging LLMs, agentic orchestration, retrieval-augmented generation (RAG), and tight integration with the client’s existing digital and enterprise systems.
You will lead architectural decisions, guide development standards, and help shape the next-generation customer experience powered by intelligent, modular agents.

Key Responsibilities

Solution Design:
Drive the architecture and solution design for the AI platform, ensuring it meets business, performance, and scalability requirements
Design patterns for prompt-driven UI generation, long-term memory usage, and multi-agent collaboration
Select appropriate frameworks and orchestrators (e.g., LangChain, LangGraph, CrewAI, Agno) based on project needs
Application Development:
Build and maintain production-grade agentic AI services in Python
Own integration patterns between schema-rendered UI, prompt handling, and inference pipelines
Implement APIs and backend components to interface with LLMs, memory stores, external tools, and enterprise systems
Develop and integrate RAG pipelines, vector stores, and structured output parsing
Contribute to re-usable libraries and accelerators
Write clean, testable code and ensure robust CI/CD and deployment pipelines are in place
Technical Leadership:
Provide technical guidance to junior and mid-level developers

Conduct code reviews and maintaining high standards of software quality

Collaborate closely with product managers, front-end developers, and Lab49’s and Client’s architecture and QA teams

Stay current with the rapidly evolving LLM landscape and proactively suggest innovations
Experience And Skills

Required experience and skills:
Bachelor's degree in Computer Science, Information Technology, or a related field.

Master’s degree is preferred
5 to 10 years of hands-on software engineering experience

Strong expertise in Python and modern backend development practices

At least 2 years implementing LLM and Agentic AI solutions
Proven delivery of production-grade conversational AI platforms or prompt-native experiences (e.g., chatbots, voice assistants, agentic workflows)
Solid understanding of cloud-native AI services, preferably on AWS
Experience working in an agile, product-oriented delivery environment
Desired experience and skills:
Experience with RAG architectures, information extraction, and vector databases is desirable
Experience with Agno is a strong plus.


Details of the hybrid model: the team normally meets for 2 days a week in the office, client work may require more presence on the client premises, especially during the integration, testing and release phases of a project