AI Systems Engineer: Build Scalable Production AI

Jisr; Riyadh; On-site; SAR 260,000 - 420,000; Full time

Job summary

Jisr seeks an AI Engineer to architect and deploy production-grade AI systems that solve real business problems. You will build scalable RAG-powered solutions and customer intelligence workflows, using LangGraph, LlamaIndex, and similar tools to handle thousands of daily users.

You will own the full lifecycle from design to deployment, with a focus on robust error handling, monitoring, and cost optimization, in a modern, fast-moving environment.

Qualifications

• Hands-on experience deploying at least one AI system to production.
• Deep understanding of RAG architectures, embeddings, vector databases.
• Experience with prompt engineering as an engineering discipline, versioned and tested.
• Production-quality Python with clean API design and proper error handling.
• Expertise in resilient systems: retry logic, exponential backoff, circuit breakers.
• Testing strategies for non-deterministic systems (we test prompts).
• Async processing, queue management, and distributed systems patterns.
• Monitoring and observability for AI systems (beyond it works).
• Cost optimization for LLM-powered applications at scale.
• Deployment pipelines and feature flagging for gradual rollouts.

Responsibilities

• Architect and deploy production-grade AI systems that solve real business problems.
• Build systems that scale from hundreds to thousands of daily users.
• Own the full lifecycle from architecture to monitoring and release.

Skills

AI Systems Engineering

Production deployments

LLM orchestration

RAG architectures

Prompt engineering

Python production code

Resilient systems

Testing non-deterministic systems

Async processing & distributed systems

Tools

LangGraph

LlamaIndex

AWS Agent Core

Job description

Jisr seeks an AI Engineer to architect and deploy production-grade AI systems that solve real business problems. You will build scalable RAG-powered solutions and customer intelligence workflows, using LangGraph, LlamaIndex, and similar tools to handle thousands of daily users.

You will own the full lifecycle from design to deployment, with a focus on robust error handling, monitoring, and cost optimization, in a modern, fast-moving environment.