Senior Agentic AI Engineer
Mondia View all jobs
- Dubai
- Permanent
- Full-time
- Design and implement agentic architectures - multi-step planners, ReAct loops, tool-use orchestration, and memory systems
- Build reliable agent pipelines that handle ambiguity, recover from failures, and know when to escalate to humans
- Integrate LLMs (Claude, GPT, open-source models) with external tools, APIs, databases, and enterprise systems
- Develop evaluation frameworks to measure agent reliability, accuracy, cost, and latency in production
- Implement guardrails, safety layers, and human-in-the-loop controls for autonomous systems
- Optimize for real-world constraints: token costs, latency budgets, rate limits, and context window management
- Collaborate with product and engineering teams to identify high-value automation opportunities across the digital entertainment portfolio
- Contribute to internal tooling and frameworks that accelerate agent development across the organization
- 5+ years of software engineering experience, with at least 1-2 years focused on LLM-based systems
- Hands-on experience building agentic systems - not just prompt engineering, but orchestration, tool use, and state management
- Strong proficiency in Python; familiarity with TypeScript is a plus
- Deep understanding of LLM APIs (Claude, OpenAI, etc.), including function calling, structured outputs, and streaming
- Experience with at least one agent framework (LangGraph, CrewAI, AutoGen, custom frameworks)
- Solid software engineering fundamentals: testing, CI/CD, observability, version control
- Experience with RAG pipelines, vector databases (Pinecone, Weaviate, pgvector), and retrieval systems
- Experience with MCP (Model Context Protocol) or similar tool-integration standards