> Markdown version of [/jobs/ext/4763174-software-engineer](https://www.wearedevelopers.com/jobs/ext/4763174-software-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Software Engineer - **Company:** Decagon - **Location:** United Kingdom - **Salary:** £125,000 - £180,000 - **Contract:** Permanent contract - **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Business Analytics Applications, User Authentication, Data Visualization, Software Debugging, Programming Tools, Python (Programming Language), Software Construction, Large Language Models, Prompt Engineering, Agentic-AI, Virtual Agents, Asynchronous Programming, Software Coding, Service Stack - **Published:** November 18, 2026 - **Apply:** https://startup.jobs/software-engineer-product-decagon-8028817 ## About the Role * 1+ years building software products, with strong product thinking * Proficient in Python, comfortable working across the entire stack * Experience translating complex technical capabilities into simple, usable interfaces * Complex systems instincts, including asynchronous programming and the failure modes that only appear at scale * A high degree of comfort debugging system failures in deep technology stacks, using whatever tool gets you to the answer * A knack for turning customer asks into clear, well-scoped product and technical specs * Judgment about when to ship fast and when to slow down and build it correctly Even better * Background with LLMs, prompt engineering, evals, or AI agent systems * Experience building developer tools, APIs, platforms, or internal tools that became customer-facing * Experience with observability, data visualization, or analytics products * Experience building security-sensitive product systems, such as authentication and data access controls * Work with multi-modal or voice models ## Description You'll design and build the systems that let customers configure, train, test, and monitor sophisticated AI agents with confidence. That means strong engineering underneath, and abstractions on top that hold up across different use cases without forking per customer. You'll work day to day with product and design: joining discovery, defining requirements, reviewing designs, and iterating through launch. You'll stay close enough to customers to understand their use cases in depth and to ensure what you're building is actually right for them. Engineers here own features end to end, from technical architecture through deployment and the iteration after it. In this role, you will * Eliminate manual work by building self-serve functionality for agent configuration, training, and deployment * Design configuration abstractions that balance power and simplicity, handling diverse enterprise use cases while staying usable by non-technical teams * Build AI-powered tooling that lets CX and ops teams create and manage complex agent workflows without writing code * Build monitoring, tracing, and analytics that surface actionable signal, so customers can see where an agent is failing and why * Handle agentic systems at scale; your work will touch critical flows for Fortune 100 companies. * Run evaluations on new text and voice models, then integrate the ones that win into production traffic