Agentic AI Engineer

Abdulaziz Al‑Zaid Professional Consulting (AZ) is building a scalable B2B SaaS platform that digitizes and automates regulated, document-heavy professional workflows — from client intake and structured data capture to quality controls, approvals, and controlled report issuance — integrated with CRM, analytics, and enterprise systems.

We are hiring a hands‑on Senior Agentic AI Engineer to design and ship production‑grade LLM agent systems that automate real workflows (not demos). You will work closely with leadership and a lean engineering team to deliver AI capabilities that are measurable, reliable, secure, and commercially deployable.

What you’ll deliver (outcomes)

• Ship production LLM/agent capabilities that reduce manual effort across intake, validation, evidence extraction, drafting, QA checks, routing, and approvals.
• Build robust agentic workflows (tool use, routing, state management) with reliability patterns (timeouts, retries, fallbacks) and clear observability.
• Implement evaluation and quality measurement (offline tests + online monitoring) to continuously improve accuracy, safety, and cost performance.
• Package repeatable AI solutions that can be deployed internally and offered to clients as deliverables (scoping → delivery → measurable outcomes).

Key responsibilities

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

Must‑have (we will screen for this)

• Proven track record shipping LLM/agent systems into production (not only POCs).
• Strong experience with tool‑using agents: function calling, API integrations, RAG, structured outputs, and reliability patterns.
• Hands‑on Python development (production code, services, testing, integrations).
• Strong understanding of backend systems, APIs, auth, data stores, and production operations.
• Ability to work fast with a lean team and own delivery end‑to‑end.

Strong advantage

• Experience in regulated / auditable workflows (approvals, audit trails, evidence, controlled issuance).
• Azure-based delivery experience (or equivalent cloud), including CI/CD and monitoring.
• Familiarity with agent orchestration frameworks (LangGraph / Semantic Kernel / AutoGen / CrewAI or similar).
• Experience building AI-enabled products with evaluation and measurement discipline.

Location

Riyadh, Saudi Arabia — On‑site (Full‑Time)

Candidates outside Riyadh are welcome if able to relocate.

How to apply

Email [email protected]

with:

• CV
• Links or brief evidence of shipped work (GitHub, demos, case summaries — redacted if needed)
• Your monthly all‑in compensation expectation + notice period
• Email subject: Senior Agentic AI Engineer – Riyadh

#Hiring #Riyadh #SaudiArabia #AIEngineer #LLM #GenAI #AgenticAI #MultiAgent #RAG #FunctionCalling #Python #Azure #SaaS #B2B