Generative AI Engineer (Saudi-based only)

Lucidya; Saudi Arabia; On-site; SAR 150,000 - 200,000; Full time

Job summary

A technology company in Saudi Arabia is looking for a Generative AI Engineer to design and implement applications powered by generative AI technologies. This role involves collaboration with product and engineering teams to create scalable AI solutions, emphasizing LLMs and system integration. Candidates should have expertise in prompt engineering, model integration, and managing AI infrastructure.

Qualifications

• Experience in developing applications using large language models (LLMs).
• Proficiency in prompt design and optimization.
• Ability to integrate third-party AI models effectively.

Responsibilities

• Build and deploy AI applications leveraging LLMs.
• Design and optimize prompts for high-quality outputs.
• Collaborate with cross-functional teams for AI integration.

Skills

LLM Application Development

Prompt Engineering

Model Integration

MLOps/AI Infrastructure Management

Data Handling

Collaboration Skills

Evaluation & Monitoring

Innovation

Job description

Overview

We are seeking a Generative AI Engineer to join our team and help design, build, and optimize applications powered by large language models (LLMs) and other generative AI technologies. This role combines deep technical expertise with creativity in prompt design, system integration, and deployment of AI-driven solutions that deliver real-world impact.

You will work closely with product, research, and engineering teams to develop scalable, reliable, and effective AI solutions—from backend infrastructure to prompt optimization.

Key Responsibilities

• LLM Application Development: Build and deploy AI-powered applications leveraging LLMs, multimodal models, and generative AI frameworks.
• Prompt Engineering: Design, test, and optimize prompts to achieve reliable, high-quality outputs for diverse use cases.
• Model Integration: Integrate third-party models (e.g., OpenAI, Anthropic, open-source LLMs) into production systems using APIs and MCP servers.
• MLOps/AI Infrastructure: Configure and manage model-serving environments, ensuring scalability, security, and high availability.
• Data Handling: Preprocess and manage datasets to fine-tune or adapt models for specific business needs.
• Collaboration: Partner with product managers, designers, and researchers to align AI capabilities with user experience goals.
• Evaluation & Monitoring: Define metrics, run experiments, and monitor generative AI systems for quality, bias, and performance.
• Innovation: Stay up to date with the latest advancements in generative AI and propose creative applications of emerging technologies.