Agentic AI Engineer📣 إعلان

About Abdulaziz AlZaid Financial Consulting

Abdulaziz AlZaid Financial Consulting is developing a scalable B2B SaaS platform designed to digitize and automate regulated, document-heavy professional workflows. This platform manages processes from client intake and structured data capture to quality controls, approvals, and controlled report issuance. It integrates seamlessly with CRM, analytics, and various enterprise systems to streamline operations.

The Role: Agentic AI Engineer

We are seeking an Agentic AI Engineer to join our team in Riyadh, Saudi Arabia. This is a full-time position requiring 0-1 years of experience. The successful candidate will be responsible for designing and delivering production-grade LLM agent systems that automate real-world workflows. You will collaborate closely with leadership and a lean engineering team to implement AI capabilities that are measurable, reliable, secure, and commercially deployable.

Key Responsibilities

• Design and implement multi-step, tool-using LLM workflows, incorporating function calling, external APIs, RAG, and structured outputs.
• Build reusable orchestration patterns for routing, memory/state management, task decomposition, guardrails, and error recovery.
• Manage LLMOps, including deployment, monitoring, prompt/version management, evaluation harnesses, and cost/latency control.
• Integrate agents with business systems such as CRM, document/report pipelines, approvals, and analytics, utilizing secure APIs and robust role/permission models.
• Establish engineering standards for AI delivery, covering testing, reliability, logging, incident response, and measurable KPIs (quality, cycle time, adoption).
• Support client-facing AI delivery as needed, assisting with requirements gathering, estimation, proof-of-concept development, and rollout.

Outcomes and Deliverables

• Ship production LLM/agent capabilities that effectively reduce manual effort across intake, validation, evidence extraction, drafting, QA checks, routing, and approvals.
• Develop robust agentic workflows with essential reliability patterns, including timeouts, retries, fallbacks, and clear observability.
• Implement comprehensive evaluation and quality measurement systems, combining offline tests with online monitoring, to continuously enhance accuracy, safety, and cost performance.
• Package repeatable AI solutions for internal deployment and client delivery, encompassing scoping, delivery, and measurable outcomes.

Required Qualifications

• Proven track record of shipping LLM/agent systems into production, beyond just Proofs of Concept (POCs).
• Strong experience with tool-using agents, including function calling, API integrations, RAG, structured outputs, and reliability patterns.
• Hands-on Python development skills for production code, services, testing, and integrations.
• Strong understanding of backend systems, APIs, authentication, data stores, and production operations.
• Ability to work efficiently within a lean team and take ownership of end-to-end delivery.

Advantageous Qualifications

• Experience in regulated or auditable workflows, such as those involving approvals, audit trails, evidence management, and controlled issuance.
• Azure-based delivery experience (or equivalent cloud platform), including CI/CD pipelines and monitoring tools.
• Familiarity with agent orchestration frameworks like LangGraph, Semantic Kernel, AutoGen, CrewAI, or similar.
• Experience in building AI-enabled products with a disciplined approach to evaluation and measurement.