About the Role
This is a remote role based in Qatar for a duration of 12 months. As an AI Engineer, you will be responsible for designing, developing, and deploying production-grade AI applications that support approved business use cases and enterprise AI platforms. This position requires a unique blend of robust software engineering expertise and practical experience in areas such as Generative AI, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), agentic systems, and enterprise integrations. The ideal candidate will possess over 5 years of software engineering experience, with a minimum of 2 years working directly on delivering AI, GenAI, or agent-based solutions in production environments.
Ready to apply for roles like this?
Unlock the company name and direct application link. Subscribers get instant access to fresh jobs across Dubai, Abu Dhabi and Riyadh, many with visa support.
Unlock employer & apply directly
Key Responsibilities
- Design, develop, and deploy production-grade AI and GenAI applications that align with business requirements.
- Translate business needs into scalable technical architectures, APIs, workflows, and AI solutions.
- Build and maintain AI agents, orchestration frameworks, MCP integrations, APIs, and connectivity with enterprise tools.
- Design and implement RAG solutions, which include ingestion, embeddings, vector search, retrieval optimization, and grounding mechanisms.
- Develop strategies for prompt, context, memory, and agent to enhance AI solution performance and reliability.
- Establish automated evaluation frameworks and testing strategies that cover accuracy, safety, performance, and retrieval quality.
- Support CI/CD, deployment, monitoring, troubleshooting, and production operations for AI solutions.
- Collaborate with architecture, security, data, and business teams to ensure compliance with enterprise standards and governance.
- Create technical documentation, operational runbooks, and knowledge-transfer materials for stakeholders and support teams.
Must Have
- Over 5 years of professional software engineering experience, including at least 2 years hands-on with LLM, Generative AI, or Agentic AI solutions.
- Proven experience delivering at least one AI, LLM, or GenAI solution into production.
- Advanced Python programming skills and proficiency in building APIs, microservices, and integration components.
- Strong expertise in software engineering best practices which include version control, testing frameworks, logging, monitoring, and secure coding.
- Practical experience with LLMs, prompt engineering, structured outputs, tool/function calling, and production troubleshooting.
- Experience designing and implementing agent-based architectures using frameworks such as Semantic Kernel, Lang Graph, Microsoft Agent Framework, or Google ADK.
- Strong familiarity with MCP servers, MCP clients, or equivalent enterprise integration patterns.
- Expertise in RAG architectures, covering chunking, embeddings, vector databases, hybrid search, reranking, and retrieval evaluation.
- Thorough understanding of context engineering, memory management, conversation state management, and prompt lifecycle management.
- Experience building automated evaluation frameworks and testing suites for AI applications.
- Familiarity with CI/CD pipelines, containers, deployment automation, and production telemetry.
- Ability to design scalable, secure, and maintainable enterprise-grade AI solutions.
- Strong stakeholder management and collaboration skills.
Good to Have
- Experience in deploying AI solutions on Microsoft Azure.
- Hands-on experience with Azure AI Foundry, Azure OpenAI, Azure AI Search, Azure Container Apps, API Management, and Application Insights.
- Familiarity with implementing Git Ops practices.
- Microsoft AI-102 Certification or other relevant AI certifications.
- Experience working in telecommunications, large enterprises, or regulated industry environments.
- Understanding of enterprise architecture governance, privacy controls, and operational support frameworks.
- Experience supporting large-scale AI platforms and operations.