AI Agent Developer

About the role

Key responsibilities

• Design planning-and-reasoning loops, task decomposition, and multi-agent orchestration.
• Integrate LLMs with external systems, databases, internal business software, and web tools through function calling and custom APIs.
• Build stateful memory, vector databases, and RAG semantic search pipelines for long-running tasks.
• Implement output parsing, error recovery, fallback mechanisms, cost controls, and safety guardrails.
• Set up production logging, tracing, and evaluation using frameworks such as LangSmith, Langfuse, or Ragas.

Technical requirements

• Strong Python proficiency, including asynchronous pipelines and clean backend API development.
• Hands-on experience with frontier LLM APIs and agent frameworks such as LangGraph, CrewAI, or LlamaIndex.
• Experience with vector databases such as Pinecone, pgvector, or Qdrant, and embedding or reranking pipelines.
• Familiarity with Docker, FastAPI, and AWS, GCP, or Azure.
• Solid software engineering practices, version control, and debugging asynchronous or non-deterministic code.

Qualifications

• At least 3 years in software engineering, including 1–2 years building production LLM, RAG, or agent-based systems.
• Bachelor’s or Master’s degree in Computer Science or Artificial Intelligence, or equivalent practical experience.
• Comfort troubleshooting non-deterministic AI outputs, infinite tool-calling loops, and edge-case failures.

Pay

• Pay is AED 3,400–15,000 per month.

Work location

• Work location is in person.