We are looking for an experienced AI Software Engineer to develop and deploy AI-powered capabilities for a large-scale enterprise platform. You will build production-grade AI applications leveraging Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), speech technologies, and real-time AI pipelines. Key Responsibility:Design, develop, and deploy AI-powered applications using Python and modern AI frameworks. Build and integrate LLM, RAG, and AI inference services into enterprise applications. Develop real-time Speech-to-Text (STT), Text-to-Speech (TTS), and speaker diarization pipelines. Build intelligent features such as AI assistants, document generation, summarization, and conversational AI. Develop low-latency streaming AI pipelines for production environments. Optimize AI models and inference performance for scalability and reliability. Integrate AI services with backend APIs and enterprise platforms. Collaborate with cross-functional teams to deliver secure, scalable AI solutions. Write clean, maintainable, and well-tested code following engineering best practices.
Required Experience:7+ years of experience in AI/ML or Generative AI application development. Strong programming experience in Python. Hands-on experience with Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). Experience integrating AI services using APIs and inference endpoints. Experience building real-time or streaming AI applications. Strong understanding of REST APIs, microservices, and cloud-native application development. Experience with Git, CI/CD, and containerized deployments.
Preferred Experience:Experience with Speech-to-Text (STT), Text-to-Speech (TTS), or speaker diarization. Experience with Microsoft Azure AI services or Azure Open AI. Experience with Lang Chain, Semantic Kernel, Llama Index, or similar orchestration frameworks. Experience working on enterprise digital transformation or AI platform projects. Familiarity with multilingual AI applications (Arabic is an advantage).