Lead AI Engineer

Responsibilities

• Design and own the end-to-end architecture of Generative and Agentic AI solutions, including orchestration, AI agents, tool/function calling, RAG, memory and state management.
• Remain hands-on with software development, building complex components and taking prototypes through to production-grade solutions.
• Define engineering standards and best practices for AI applications, including reference architectures, testing and evaluation strategies, guardrails, observability and CI/CD.
• Design scalable, secure and reliable AI systems, considering performance, latency, cost, monitoring and production requirements.
• Evaluate and select appropriate LLMs, frameworks, platforms and tools based on technical and business requirements.
• Lead technical design and code reviews, mentor other engineers and contribute to raising engineering standards across the team.
• Work directly with clients and senior stakeholders to translate business requirements into technical architectures and clearly communicate technical decisions and trade-offs.
• Contribute to technical documentation, reference architectures and thought leadership around Generative and Agentic AI.
• Skills and Experience
• Essential skills to succeed
• 8+ years of professional experience in Software Engineering, Backend Engineering, or similar engineering roles, including experience designing and building enterprise-grade systems.
• Strong hands-on software engineering skills and experience writing high-quality production code, with Python or an equivalent programming language.
• Demonstrable experience designing and developing LLM and Agentic AI applications, including AI agents, LLM orchestration and tool/function calling.
• Strong understanding of RAG architectures, retrieval approaches and vector-based search.
• Experience with agentic frameworks and integration approaches such as LangChain, LangGraph, MCP or comparable technologies.
• Understanding of how to test and evaluate non-deterministic AI systems, including LLM/agent evaluation, monitoring and observability.
• Strong software architecture and engineering fundamentals, including APIs, distributed systems, integration patterns and production reliability.