AI Forward Deployed Engineer

Jobmaze FZ LLC; Riyadh; On-site; SAR 350,000 - 550,000; Full time

Job summary

Jobmaze FZ LLC in Riyadh, Saudi Arabia, is hiring an AI Forward Deployed Engineer (FDE) to design, deploy, and optimize production-grade Agentic AI solutions for enterprise customers.

The role blends software engineering, cybersecurity, and AI, working directly with customers to build integrations, workflows, and guardrails using LangChain, LangGraph, Python, and cloud services.

Qualifications

• Requires strong Python engineering skills and hands-on experience building AI systems.
• Proven experience delivering LLM/Agentic AI applications in enterprise environments.
• Experience with LangChain and LangGraph is essential.
• Knowledge of multi-agent architectures, tool calling, state, memory, and orchestration is required.
• Understanding of cybersecurity operations (SOC, SIEM, EDR/XDR, SOAR, MITRE ATT&CK) is desirable.

Responsibilities

• Design and deploy production-grade AI agents and multi-agent workflows.
• Build Agentic AI solutions using LangChain, LangGraph, and similar frameworks.
• Develop integrations, tools, APIs, workflows, and agent graphs with Python.
• Integrate AI agents with enterprise cybersecurity platforms and customer infrastructure.
• Create AI workflows for security incident response, triage, and automation.
• Troubleshoot AI behaviour, improve guardrails, performance and reliability.
• Work directly with enterprise customers, SOC teams, and MSSPs to resolve security challenges.

Skills

Python engineering

LLM/Agentic AI apps

LangGraph/LangChain

Multi-agent architectures

Cybersecurity ops awareness

Tools

Docker

Kubernetes

Linux

Git

CI/CD

FastAPI

Pydantic

REST APIs

Job description

We are hiring an experienced AI Forward Deployed Engineer (FDE) for our client in Saudi Arabia.

This is a highly technical, hands-on, customer-facing role at the intersection of Agentic AI, software engineering, cybersecurity, and enterprise deployment.

The successful candidate will work directly with customers and security teams to design, build, integrate, deploy, troubleshoot, and continuously improve production-grade Agentic AI solutions.

Key Responsibilities:

• Design and deploy production-grade AI agents and multi-agent workflows
• Build Agentic AI solutions using LangChain, LangGraph, and similar frameworks
• Develop custom integrations, tools, APIs, workflows, and agent graphs using Python
• Integrate AI agents with enterprise cybersecurity platforms and customer infrastructure
• Build AI workflows for security alert triage, investigation, threat hunting, incident response, and automation
• Troubleshoot AI behaviour and improve agent accuracy, reliability, guardrails, and performance
• Take solutions from idea code integration deployment production
• Work directly with enterprise customers, SOC teams, and MSSPs to solve real-world security challenges

Key Technical Requirements:

• Excellent hands-on Python engineering skills – mandatory
• Proven experience building LLM / Agentic AI applications
• Strong experience with LangGraph and/or LangChain
• REST APIs, WebSockets, FastAPI, Pydantic & API integrations
• LLMs, RAG, embeddings, vector search & structured outputs
• Multi-agent architectures, tool/function calling, state, memory & orchestration
• MCP (Model Context Protocol) and AI agent infrastructure
• Docker, Kubernetes, Linux, Git & CI/CD
• Azure, AWS or GCP experience
• Understanding of cybersecurity operations including SOC, SIEM, EDR/XDR, SOAR, Incident Response & MITRE ATT&CK
• Ability to deploy and troubleshoot solutions in complex enterprise environments

Experience integrating technologies such as Microsoft Sentinel/Defender, CrowdStrike, Splunk, Palo Alto, Fortinet, Elastic or OpenSearch will be a strong advantage.

We are particularly interested in engineers who have built and deployed real Agentic AI systems, not just experimented with prompts or standalone LLM applications.

Only shortlisted candidates will be contacted.