About The Role

To define technical approach to AI agents, orchestration frameworks, and responsible AI practices while working closely with engineering teams, product managers, and business stakeholders to bring cutting-edge AI capabilities to production.

Lead AI solutions design and implementation

Serve as the primary technical advisor on generative AI initiatives
Lead proof-of-concept development and architectural decision records
Mentor engineering teams on agentic AI patterns and best practices
Evaluate emerging technologies and maintain technical roadmaps
Design and architect AI agent systems and multi-agent workflows for enterprise use cases
Evaluate and implement agent frameworks including LangGraph, Microsoft Agent Framework, OpenAI Agents SDK, Google Agent-to-Agent (A2A), and emerging standard • Architect tool-use patterns, function calling, MCP, and agent-to-agent communication protocols
Design for agent observability, debugging, and human-in-the-loop workflows
Design retrieval-augmented generation architectures and architect vector database solutions, embedding strategies, implement chunking strategies, hybrid search, and re- ranking approaches for optimal retrieval performance
Design knowledge graphs and structured data integration with generative AI systems
Lead architecture decisions across cloud AI platforms including Azure AI Foundry, Google Vertex AI, OpenAI APIs, and open-source Gen AI models
Design prompt management, versioning, and optimization pipelines
Architect for multi-model strategies, model routing, and fallback patterns
Establish patterns for cost optimization, latency management, and scaling LLM workloads
Define comprehensive evaluation frameworks for LLM applications and agent systems
Implement automated evaluation pipelines using frameworks such as RAGAS, DeepEval, and custom evaluation harnesses
Establish benchmarks for response quality, factual accuracy, task completion, and user satisfaction
Champion responsible AI practices including safety, fairness, transparency, and privacy
Implement guardrails, content filtering, and output validation systems
Design for prompt injection prevention, data leakage protection, and secure agent execution
Ensure compliance with emerging AI regulations and industry standards
Bachelor's degree in Computer Science, Engineering, or related field; Master's preferred. Arabic Speaker.
8+ years of experience in software engineering or architecture roles
3+ years of hands-on experience building LLM-powered applications in production
Deep expertise in AI agent architectures, orchestration patterns, and workflow design
Strong experience with at least two of the following: LangChain/LangGraph, Microsoft Semantic Kernel/Agent Framework, OpenAI Agents SDK, Google Vertex AI Agent Builder
Proven experience designing and implementing Advanced RAG Systems and Agentic AI
Proficiency in Python and experience with async programming patterns
Hands-on experience with cloud AI platforms (Azure AI Foundry or Google Vertex AI)
Strong understanding of Gen AI models’ fundamentals including prompting, fine-tuning, context windows, and token economics

Preferred Qualifications

Experience implementing Model Context Protocol (MCP), Google Agent-to-Agent (A2A) protocol, and multi-agent communication patterns
Experience building AI Evals pipelines and AI quality assurance systems
Knowledge of advanced RAG techniques: query decomposition, multi-hop reasoning, GraphRAG
Experience with AI observability tools
Background in AI safety, red-teaming, or responsible AI implementation.

Skills & Competencies

Systems thinking with ability to design for complexity and emergence in agentic systems
Strong communication skills to convey AI concepts to diverse audiences
Pragmatic approach balancing innovation with production readiness
Ability to rapidly learn evolving AI technologies
Commitment to ethical AI development and user safety
Collaborative mindset with ability to influence across organizational boundaries