AI Engineer

About the Role

SoftServe is seeking an AI Engineer to join their team in Saudi Arabia. This full-time role focuses on designing and delivering Generative AI (GenAI) solutions within a bespoke, on-premise AI platform named Arthur. The successful candidate will be responsible for building production-ready AI applications and integrating enterprise systems and data with various Large Language Model (LLM) providers.

Key Responsibilities

• Design, develop, and productionize GenAI/LLM applications and use cases.
• Build Retrieval Augmented Generation (RAG), agentic AI, and tool-enabled workflows using enterprise data and systems.
• Integrate AI solutions with APIs, databases, applications, and external LLM providers, including Anthropic, OpenAI, and Google.
• Develop effective prompt and context engineering approaches, incorporating structured outputs and guardrails.
• Implement testing, LLM evaluation, monitoring, and observability to ensure solution quality and reliability.
• Apply appropriate security, data privacy, and Responsible AI controls.
• Collaborate with architects, platform engineers, business Subject Matter Experts (SMEs), and other delivery teams.
• Contribute reusable components, integration patterns, and engineering best practices.

Required Qualifications and Experience

Candidates should possess 5-10 years of relevant experience and demonstrate a strong background in software engineering and AI development.

• Strong Python and general software engineering experience.
• Hands-on experience developing GenAI/LLM solutions in a production or enterprise environment.
• Experience with RAG, embeddings, vector/semantic search, and enterprise data.
• Experience with agentic AI, tool/function calling, and/or Multi-Party Computation (MCP).
• Familiarity with multiple LLM providers such as Anthropic Claude, OpenAI, and Google/Gemini.
• Strong API and enterprise integration skills.
• Understanding of LLM evaluation, guardrails, observability, and AI security.
• Experience with Docker/Kubernetes and on-premise/private environments is desirable.

Key Skills and Mindset

• Strong problem-solving, communication, and stakeholder engagement skills.
• A model-agnostic engineering mindset, with the ability to work across different LLMs rather than being dependent on a specific hyperscaler.

Work Type

This is a full-time position.

Application Process

The salary for this position will be disclosed during the application process.