Generative AI Engineer

Fikrah Ventures; Dammam; On-site; SAR 260,000 - 420,000; Full time

Job summary

Fikrah Ventures is seeking a Generative AI Engineer to design, develop, and deploy AI-powered solutions using LLMs and generative AI frameworks. You will build autonomous AI agents, orchestrate multi-agent workflows, and integrate AI with enterprise systems.

The role focuses on memory/context management, tool usage, and scalable backend services with Python. Strong emphasis on security, observability, and production-grade engineering.

Qualifications

• 1+ years of experience building, optimizing, and deploying production-ready applications powered by Large Language Models (LLMs).
• Bachelor's degree in Computer Science.
• English — Advanced proficiency
• Arabic — Preferred.

Responsibilities

• Design autonomous AI agents with defined roles, goals, and responsibilities.
• Build multi-agent collaboration, delegation, and coordination workflows.
• Implement planning, reasoning, and task execution across complex processes.
• Develop integration with internal systems, databases, and external APIs.
• Create reusable and modular agent components and workflows.
• Develop production-grade AI services using Python and modern backend technologies.
• Implement logging, tracing, monitoring and debugging for agent workflows.
• Deploy AI solutions on cloud platforms with security and privacy best practices.

Skills

Agentic AI Design

Multi-Agent Collaboration

Problem Solving

LLM & Prompt Engineering

System Integration

Adaptability

Teamwork

Attention to Detail

Education

Bachelor's degree in Computer Science

Tools

LangGraph

Semantic Kernel

Microsoft Agent Framework

Job description

We are seeking a Generative AI Engineer to join our technology team and design, develop, and deploy AI-powered solutions using Large Language Models (LLMs), generative AI frameworks, and modern machine learning technologies.

The role is responsible for designing and building AI agents and multi-agent systems that can reason, plan, collaborate, and execute complex tasks across business and technical workflows. This includes agent orchestration, communication and coordination between specialized agents, enterprise system and external tool integration, memory and context management, and reliable agentic workflows using LLMs, RAG, APIs, document processing, prompt engineering, vector databases, embeddings, machine learning principles, and automation frameworks.

Key Accountabilities

1. Agentic AI & Multi-Agent Architecture Design autonomous AI agents with defined roles, goals, and responsibilities. Build multi-agent collaboration, delegation, and coordination workflows. Implement planning, reasoning, and task execution across complex processes. JD - Generative AI Engineer
2. Large Language Models & Generative AI Integrate and optimize LLMs for enterprise and business use cases. Develop effective prompt engineering and structured output techniques. Implement function calling, tool usage, and model-driven workflows.
3. RAG, Memory & Context Engineering Build Retrieval-Augmented Generation pipelines using enterprise data. Implement short-term and long-term memory for AI agents. Optimize embeddings, vector search, and context management strategies.
4. Agent Tools, APIs & System Integration Connect AI agents with internal systems, databases, and external APIs. Develop tools that enable agents to perform business and technical actions. Integrate agents with enterprise platforms and automation workflows.
5. AI Frameworks & Orchestration Develop agent workflows using frameworks such as LangGraph, Semantic Kernel, and Microsoft Agent Framework. Manage multi-step agent execution and orchestration logic. Design reusable and modular agent components and workflows.
6. Software Engineering & Backend Development Develop production-grade AI services using Python and modern backend technologies. Build scalable APIs, microservices, and asynchronous processing workflows. Apply testing, version control, containerization, and software engineering best practices.
7. AI Evaluation, Observability & Reliability Evaluate agent accuracy, reasoning quality, and task completion performance. Implement logging, tracing, monitoring, and debugging for agent workflows. Apply guardrails, fallback mechanisms, and hallucination-reduction techniques.
8. Cloud AI, Security & Production Deployment Deploy and operate AI solutions on cloud platforms and managed AI services. Apply security, access control, privacy, and responsible AI practices. Optimize scalability, latency, resource utilization, and AI infrastructure costs.

Competencies

Core

• Agentic AI Design — Ability to design and develop autonomous AI agents capable of reasoning, planning, decision-making, and executing complex tasks
• Multi-Agent Collaboration — Strong understanding of multi-agent architectures, including agent roles, coordination, delegation, communication, and orchestration between specialized agents
• Problem Solving — Strong analytical and troubleshooting skills for complex AI, integration, and workflow-related challenges
• LLM & Prompt Engineering — Ability to work effectively with Large Language Models, prompt engineering, structured outputs, tool calling, and model-driven workflows
• System Integration — Ability to integrate AI agents with APIs, databases, enterprise applications, external tools, and business workflows
• Adaptability & Continuous Learning — Ability to quickly learn and adapt to evolving AI models, agent frameworks, tools, technologies, and industry practices
• Teamwork & Collaboration — Ability to work with software engineers, data teams, product teams, and business stakeholders
• Attention to Detail — Strong focus on AI output quality, agent behaviour, reliability, security, performance, and accuracy.

Soft

• Excellent communication skills
• Excellent teamwork skills
• Excellent email writing and etiquette skills.

Job Specifications

Industry: Information Technology

Experience:

1+ years of experience building, optimizing, and deploying production-ready applications powered by Large Language Models (LLMs).

Education:

Bachelor's degree in Computer Science.

Languages:

• English — Advanced proficiency
• Arabic — Preferred.