Agentic AI Engineer

Webook; Saudi Arabia; On-site; SAR 180,000 - 320,000; Full time

Job summary

Webook, Saudi Arabia’s leading event ticketing and experience platform, seeks an AI/ML engineer to design and implement multi-step agents that can plan, retrieve, act, and verify with robust safety and observability. You will craft agent loops and tooling, integrating LangChain-like workflows and tool calling.

Responsibilities include combining RAG with agents, building evaluation methods, and optimizing for reliability, safety, and cost while working with cloud services and containerized

Qualifications

• Strong Python engineering skills with async patterns and robust error handling.
• Practical RAG skills: vector databases, indexing pipelines, and retrieval quality tuning.
• Systems thinking: queues, retries, idempotency, caching, and concurrency control.
• Security and safety for agents (prompt injection, tool scoping, least privilege).

Responsibilities

• Build multi-step tool-using agents that plan, retrieve, act, and verify.
• Architect agent loops (planning, memory, retrieval, tool use, self-verification).
• Implement tools, functions, APIs, DB queries, files, and MCP-style interfaces.
• Combine RAG with agents (chunking, embeddings, retrieval, reranking, grounding).
• Add guardrails, execution sandboxes, permissions, rate limits, and PII policies.
• Build evaluation methods for agent task success, autonomy depth, and recovery rate.
• Optimize for reliability, determinism where needed, and cost.

Skills

Python engineering

Async patterns

Error handling

Agent tooling & safety

RAG fundamentals

Tools

GCP

AWS

Docker

Kubernetes

Message buses/streams

Job description

Overview

Do you want to love what you do at work, make a difference, and transform people’s lives? Do you want to work with a team that disrupts the normal, boring, and average? If yes, this is the job you are looking for. webook.com is Saudi Arabia’s #1 event ticketing and experience booking platform, delivering technology, features, agility, and revenue to some of the largest mega events in the Kingdom, with sales surpassing over 2 billion.

Responsibilities

• Build multi-step tool-using agents that plan, retrieve, act, and verify. Design agent architectures, integrate tools/APIs, and deliver robust execution with safety and observability.
• Architect agent loops (planning, memory, retrieval, tool use, self-verification).
• Implement tools, functions, APIs, DB queries, files, and MCP-style interfaces.
• Combine RAG with agents (chunking, embeddings, retrieval, reranking, grounding).
• Add guardrails, execution sandboxes, permissions, rate limits, and PII policies.
• Build evaluation methods for agent task success, autonomy depth, and recovery rate.
• Optimize for reliability, determinism where needed, and cost.
• Demonstrate production experience with LangChain, CrewAI, or similar, and function/tool calling.

Qualifications

• Strong Python engineering skills with async patterns and robust error handling.
• Practical RAG skills: vector databases, indexing pipelines, and retrieval quality tuning.
• Systems thinking: queues, retries, idempotency, caching, and concurrency control.
• Security and safety for agents (prompt injection, tool scoping, least privilege).

Nice-to-Haves

• GCP and AWS experience; Docker and Kubernetes; message buses/streams.
• LLM evaluation frameworks; synthetic data generation.
• Graph-based planning, constraint solvers, or program-of-thought techniques.
• Production experience with LangChain/CrewAI (or similar) and function/tool calling.