AI Engineer – Build Scalable LLM Solutions

About the role

We are seeking an experienced AI Engineer to design, build, deploy, and scale AI‑powered product capabilities for our AI/LLM product engineering team in Amman. You will turn cutting‑edge AI concepts and prototypes into reliable, production‑ready solutions while collaborating closely with engineering, product, data, and AI researchers.

Key responsibilities

• Integrate AI/LLM services using cloud platforms such as AWS Bedrock and Azure OpenAI.
• Design and implement agentic workflows and LLM‑driven features with frameworks like LangGraph or LangChain.
• Develop Retrieval‑Augmented Generation pipelines, vector embeddings, and prompt‑engineering workflows.
• Convert prototypes into scalable, secure, maintainable production systems with proper testing and CI/CD.
• Leverage AI‑assisted development tools (GitHub Copilot, Claude Code, Cursor) while ensuring code quality and security.
• Collaborate with product managers, data engineers, software engineers, and AI researchers to solve complex technical challenges.
• Evaluate and improve AI models using metrics for quality, latency, and performance.

Required profile

• 3–7 years of professional experience in AI engineering, machine‑learning engineering, or software engineering.
• Hands‑on experience building AI/LLM applications, prompt engineering, and tool/function calling.
• Strong Python programming skills and solid software‑engineering fundamentals (OOP, design patterns, clean code).
• Experience with REST/gRPC APIs, data processing, unit and integration testing, CI/CD pipelines, and Git.
• Ability to work independently and within distributed, cross‑functional teams.

Required skills

• Python
• AWS (including Bedrock) and Azure (including OpenAI)
• LangGraph, LangChain
• RAG, vector embeddings, prompt engineering
• GitHub Copilot, Claude Code, Cursor
• REST, gRPC, CI/CD, Git
• Docker, Kubernetes
• Vector databases (Milvus, Pinecone, Qdrant)
• LangSmith, Phoenix (AI evaluation/observability)