Software Engineer (Agentic)

Software Engineer | Agentic AI | London Competitive Salary + Equity + Outstanding Benefits Large language models are changing what software can do. We're partnering with a well-funded technology company building AI agents that can reason, use tools, interact with systems and solve complex problems autonomously . They're looking for a Software Engineer who wants to work at the cutting edge of agentic AI — designing, building and deploying the systems that allow AI agents to operate reliably in real-world environments. This isn't a role where you'll simply be wrapping an LLM API around an existing product. You'll be working on the engineering and architecture behind intelligent agents , figuring out how they should reason, interact with tools, retain context, coordinate tasks and operate reliably at scale. What you'll get to do * Design and build AI agents capable of completing complex, multi-step tasks * Develop agent architectures covering reasoning, planning, tool use, memory and decision-making * Build systems that allow agents to interact with APIs, databases, external services and other software * Experiment with different approaches to agent orchestration and multi-agent systems * Build evaluation frameworks to understand how agents perform and continuously improve their reliability * Work on agent workflows, context management, retrieval and LLM infrastructure * Turn research and experimentation into robust, production-quality software * Solve challenging problems around agent reliability, autonomy, latency and scalability * Work closely with highly capable engineers and researchers across AI and software * Have significant influence over the architecture and technical direction of the platform You'll be a strong fit if you have * Strong software engineering fundamentals and experience building production-quality systems * Strong experience with Python , or another modern programming language * A genuine interest in LLMs, agentic AI and the future of AI-powered software * Experience building with LLMs, AI agents or agent frameworks — professionally or through serious personal projects * An understanding of concepts such as tool calling, RAG, agent orchestration, context management or multi-agent systems * Strong problem-solving ability and the desire to work on technically difficult, ambiguous problems * The ability to learn quickly and work across both established engineering practices and rapidly evolving AI technology You don't need to have spent your career working in AI. Strong software engineers who have built interesting agentic AI projects and understand where the technology is heading are very much encouraged to apply. What you'll get in return * Cutting-edge AI: Work directly on the next generation of AI software rather than simply consuming existing models * Technical ownership: Have a genuine say in how the company's agent architecture evolves * Hard engineering problems: Work on reliability, orchestration, evaluation, scalability and autonomy * Fast development: Work alongside highly capable engineers and AI specialists * Real impact: Build agents that solve meaningful problems rather than toy demonstrations * Variety: Constantly experiment with new models, techniques and approaches as the field evolves * Equity: Have genuine ownership in the company you're helping to build If you're a strong software engineer who wants to build the agents themselves — not just build software around AI — I'd be happy to tell you more.