Location: Remote / Hybrid / On-site (Saudi Arabia)
Employment Type: Full-time / Part-time / Contract-based
Start Date: Immediate
About the Role
We are seeking a driven AI Engineer to build and deploy production-grade AI applications solving real business challenges. You’ll focus on RAG systems, AI agents, workflow automation, document intelligence, and enterprise AI integration.
Key Responsibilities
– Design and build complete RAG (Retrieval-Augmented Generation) pipelines
– Develop intelligent AI agents that interact with APIs, databases, and business tools
– Build data ingestion pipelines for PDFs, DOCX, Excel files, emails, cloud storage, and enterprise systems
– Apply document chunking strategies, embedding generation, vector search, and reranking
– Integrate Large Language Models (LLMs) into scalable, production-ready applications
– Build secure backend services with access control, PII protection, audit logging, and human-approval mechanisms
– Optimize AI pipelines for performance, accuracy, and cost efficiency
– Debug production issues and continuously improve deployed AI systems
– Collaborate closely with product, engineering, and business teams to deliver high-impact AI solutions
Required Skills
AI & Generative AI
– Practical experience building at least one complete AI application
– Strong understanding of Retrieval-Augmented Generation (RAG)
– Knowledge of embeddings, semantic search, prompt engineering, and LLM integration
– Experience evaluating and improving AI response quality
Agentic AI
Hands-on experience building AI agents that can:
– Call REST APIs
– Query databases
– Execute multi-step workflows
– Use external tools
– Interact with enterprise software
– Automate business processes
Software Engineering
Strong experience with:
– Python
– FastAPI
– Async programming
– REST APIs
– Git
– Software architecture
– Debugging and testing
– Clean, maintainable code
Databases & Infrastructure
Experience with one or more of the following:
– PostgreSQL
– ChromaDB
– FAISS
– pgvector
– Redis
– Docker
– Azure, AWS, or Google Cloud
Preferred Qualifications (a plus)
– LangGraph
– OpenAI Agents SDK
– LangChain
– LlamaIndex
– CrewAI
– MCP (Model Context Protocol)
– OCR technologies
– Azure AI Foundry
– CI/CD pipelines
– Kubernetes
– Monitoring and observability tools
What We’re Looking For
We’re looking for engineers who:
– Enjoy solving complex technical problems
– Build production-ready software rather than prototypes
– Take ownership from idea to deployment
– Learn quickly and adapt to new technologies
– Write clean, scalable, and maintainable code
– Communicate effectively and work well in collaborative teams
– Focus on delivering real business outcomes through AI
Application Requirements
Please send the following:
– Updated Resume/CV
– GitHub profile or portfolio website
– One AI, RAG, or Agentic AI project
– Answers to the technical assessment questions (if applicable)
Email: afransami.work@gmail.com
Subject: AI Engineer Application – [Your Full Name]
Our Values
We believe great AI products are built by engineers who are curious, practical, and committed to continuous learning. We value integrity, ownership, collaboration, and craftsmanship over titles or buzzwords. If you’re excited about building real AI systems that make an impact, we’d love to hear from you.