We are supporting a product-led technology company building advanced agentic AI systems that operate autonomously in real-world environments.
This is an opportunity to work on AI that does more than generate responses. You will be building intelligent agents that can reason, plan, take action, and continuously adapt. These systems sit at the core of the product and are already being used by customers at scale.
You will be joining a highly technical team working on some of the hardest problems in applied AI today. The focus is on shipping robust, production-ready agentic systems, not experiments or research projects.
About the role:In this role, you will design, build, and deploy agentic AI systems capable of solving complex, multi-step problems autonomously. You will work closely with product and engineering teams to turn business challenges into intelligent agent workflows that deliver real outcomes.
Your responsibilities will include:Designing agentic architectures including planning, execution, memory, and feedback loops Building agents that use RAG pipelines to retrieve and reason over proprietary knowledge Implementing embeddings and vector search to support semantic retrieval and long-term agent memory Integrating LLMs with tools, APIs, databases, and internal services Developing evaluation frameworks to measure agent accuracy, reliability, and failure modes Optimising performance, latency, and cost for AI systems running in production Debugging agent behaviour in complex, real-world scenarios
About you:You are a senior-level AI engineer with strong hands-on experience building and deploying intelligent systems. You understand how LLMs behave in production, including their limitations, and you are comfortable designing around them.
You will bring:Strong Python engineering skills and experience shipping production-grade AI systems Hands-on experience with agentic AI, RAG pipelines, embeddings, and vector search Solid understanding of semantic retrieval, context management, and knowledge grounding Experience evaluating and improving LLM-driven systems beyond simple accuracy metrics A product mindset focused on delivering reliable outcomes Comfort working in ambiguous problem spaces with high ownership
If you are excited by the challenge of building AI agents that actually work in the real world, this is a role worth exploring.