مهندس ذكاء اصطناعي – نماذج اللغات الكبيرة (LLM) ووكلاء الذكاء الاصطناعي | عن بُعد

We're looking for an AI Engineer with hands-on experience building production-ready AI systems, particularly LLM agents, Retrieval-Augmented Generation (RAG), conversational memory, and tool integrations.

If you're passionate about building reliable, scalable AI solutions and turning cutting-edge AI capabilities into real-world products, we'd love to hear from you!

What You'll Do

• Build, optimize, and maintain AI agents and multi-step workflows.
• Implement RAG pipelines, embeddings, and semantic search.
• Develop conversational memory and user-context management systems.
• Integrate AI agents with APIs, external services, and platform tools.
• Implement function calling, tool calling, and structured outputs.
• Improve prompt engineering, response quality, reliability, and guardrails.
• Build AI evaluation frameworks and automated testing workflows.
• Collaborate with Backend, Mobile, Product, and QA teams to deliver production-ready AI features.

What We're Looking For

• Strong programming skills in Python.
• Hands-on experience building LLM-powered applications and AI agents.
• Experience working with OpenAI APIs or other LLM providers.
• Practical knowledge of RAG, embeddings, vector databases, and semantic search.
• Experience with LangChain, LangGraph, or similar AI frameworks.
• Experience building production APIs using FastAPI.
• Strong understanding of function calling, tool integration, and structured outputs.
• Excellent debugging, analytical, and problem-solving skills.

Nice to Have

Experience with any of the following technologies:

• Qdrant and PostgreSQL
• LangMem or similar AI memory solutions
• OpenRouter
• AWS and cloud-based AI deployments
• Server-Sent Events (SSE) and WebSockets
• AI evaluation, monitoring, and testing systems

Why Join Us?

• Build real-world AI agents and intelligent workflows.
• Solve challenging problems involving memory, context, retrieval, and AI reliability.
• Collaborate with cross-functional teams in a remote-first environment.