Job Description

Roles & Responsibilities

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

Role Overview

Build multi-step, tool-using agents that plan, retrieve, act, and verify. You ll design agent architectures, integrate tools/APIs, and deliver robust execution with safety and observability.

Key Responsibilities :

• 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, PII policies.
• Build evaluation for agents (task success, autonomy depth, recovery rate).
• Optimize for reliability, determinism where needed, and cost.
• Production experience with LangChain/CrewAI (or similar) and function/tool calling.
• Strong Python engineering; async patterns; robust error handling.
• Practical RAG skills: vector DBs, indexing pipelines, and retrieval quality tuning.
• Systems thinking: queues, retries, idempotency, caching, concurrency control.
• Security & safety for agents (prompt injection, tool scoping, least privilege).

Nice-to-Haves

• GCP/AWS, Docker/Kubernetes; message buses/streams.
• LLM evaluation frameworks; synthetic data generation.
• Graph-based planning, constraint solvers, or program-of-thought techniques.

Desired Candidate Profile

• Production experience with LangChain/CrewAI (or similar) and function/tool calling.
• Strong Python engineering; async patterns; robust error handling.
• Practical RAG skills: vector DBs, indexing pipelines, and retrieval quality tuning.
• Systems thinking: queues, retries, idempotency, caching, concurrency control.
• Security & safety for agents (prompt injection, tool scoping, least privilege).

• GCP/AWS, Docker/Kubernetes; message buses/streams.
• LLM evaluation frameworks; synthetic data generation.
• Graph-based planning, constraint solvers, or program-of-thought techniques.