Artificial Intelligence Engineer
Our client is a fast-growing international technology organisation building a production-grade AI agent platform to support and transform business operations across multiple global entities.
They are investing heavily in generative AI and autonomous systems, focusing on scaling reliable, cost-efficient AI solutions across the enterprise. The environment is fast-paced, highly collaborative, and engineering-led, with a strong emphasis on robustness, observability, and real-world impact.
Role Overview
We are seeking an AI Engineer with a strong backend engineering background to design, build, and scale a modern AI agent platform. This role focuses on bridging experimental AI and production-grade systems - ensuring reliability, performance, and scalability of agentic workflows. You will work across platform engineering, AI orchestration, and system reliability, contributing to the standardisation of AI development across the organization.
Key Responsibilities
- Design and evolve an internal AI agent platform (Python-based)
- Improve observability, context handling, and token efficiency
- Integrate modern LLMs (e.g. Claude, Gemini) into modular backend systems
Autonomous Agent Development
- Build reasoning chains, workflows, and agent orchestration logic
- Investigate and resolve reasoning failures and hallucinations
- Implement continuous evaluation and feedback loops to improve accuracy
Reliability & Scalability
- Define and implement logging, monitoring, and error-handling standards
- Ensure production-grade stability for AI systems at scale
- Build reusable frameworks and patterns for consistent agent development
- Work closely with cross-functional teams (e.g. operations, support)
- Deliver AI solutions that reduce manual effort and improve efficiency
- Contribute to shared platform ownership and infrastructure evolution
Required Skills & Experience
- Strong backend engineering background with Python (expert level)
- Experience building APIs and distributed systems (REST / gRPC)
- Hands-on experience with LLMs / AI APIs and agent frameworks
- Familiarity with Docker, cloud platforms, and scalable architectures
- Experience designing reliable, observable, and maintainable systems
- Strong debugging mindset - ability to identify root causes in complex systems
Preferred Experience
- Exposure to agent frameworks (e.g. Google ADK or similar)
- Experience with token optimisation and cost control in LLM systems
- Knowledge of monitoring, logging, and production AI evaluation techniques