Senior AI Engineer (RAG • LangGraph • Multimodal Retrieval • Cloud AI)

Location: Remote/Hybrid – Egypt
Company: SMEtools / Knowcap.ai

We are looking for a Senior AI Engineer to help us scale and optimize advanced AI products, including RAG-powered knowledge assistants, multimodal retrieval systems, and optimized LLM workflows. If you’re passionate about architecture, efficiency, and building real, user-impacting AI systems — we want you.

• Architect and implement end-to-end RAG systems, including semantic indexing, chunking, and hybrid retrievers.
• Build intelligent agents using LangGraph and LangChain with multi-step reasoning and orchestration.
• Develop multimodal retrievers (audio, text, images, PDFs) and integrate them with our product workflows.
• Optimize token consumption, performance, and latency across models and providers.
• Integrate and deploy AI models including OpenAI, Gemini (Google AI), and AWS Bedrock.
• Build backend components in Python (FastAPI, serverless functions, pipelines).
• Manage and integrate with Firebase, including Firestore, Cloud Functions, and authentication flows.
• Deploy and scale workloads on Google Cloud or AWS (Compute, Functions, Storage, Vectors).
• Collaborate closely with product and engineering teams to rapidly prototype and ship features.

Required Skills

• Strong hands-on experience with RAG architecture, vector search, semantic search, and embeddings.
• Deep understanding of chunking strategies, indexing, metadata techniques, and retrieval evaluation.
• Proficiency in LangGraph (preferred) or LangChain for agent and workflow development.
• Experience working with Gemini models (Google AI) and/or AWS AI services.
• Expertise in Python for AI model integration, backend logic, and data pipelines.
• Strong understanding of Firebase ecosystem (Firestore, Storage, Functions).
• Knowledge in tokenization, cost optimization, caching, and inference scaling.
• Experience building multimodal retrieval systems.

Bonus Points

• Experience using Google Cloud Vertex AI or AWS Bedrock for deploying and evaluating models.
• Exposure to embedding model selection, fine-tuning, or model evaluation frameworks.
• Strong background in designing production-grade architectures (monitoring, logging, scalability).
• Experience integrating AI into SaaS platforms or enterprise workflows.