AI Engineer

ABOUT THE ROLE We are looking for forward-thinking, high-performing AI Engineers who are excited to pioneer the future of AI-driven engineering at Paysend. In this role, you will work hands-on with Claude Code and the Anthropic API to design, harden, and ship agentic systems that write, review, test, and deploy code. This is a high-impact, build-and-own opportunity: you will take cutting-edge AI prototypes and turn them into resilient production infrastructure - directly empowering our global engineering teams, accelerating our product velocity, and helping us solidify Paysend as the definitive end-to-end payment infrastructure for the modern world. THE ENGINEERING PROBLEM The problem is not to make an LLM generate code. The problem is to make AI-assisted and agentic software delivery reliable enough to become part of normal engineering work. These systems operate inside real software delivery workflows. They need to deal with incomplete context, failed execution, incorrect assumptions, external dependencies, changing repository state, and cases where an agent should not continue on its own. This means designing clear execution boundaries, decision points, observability, recovery and escalation paths, not only the agent behaviour itself. The role includes shaping how these systems work, not only implementing integrations with existing AI tools. WHAT YOU'LL DO Design end-to-end AI-assisted delivery workflows, including agent responsibilities, execution boundaries, decision points, human intervention, failure handling, recovery, and escalation Design and refine AI-driven pipelines that automate coding, code review, testing, and deployment tasks Build and optimise agentic workflows using Claude Code and the Anthropic API, including custom tooling, MCP server integrations, sub-agents, and stateful orchestration logic Engineer robust prompts, benchmark suites, and automated eval datasets; measure and improve pipeline accuracy, latency, and API costs Define workflow-specific success criteria and operational evidence, including correctness, reliability, intervention and escalation rates, failure modes, and recovery effectiveness Integrate core Anthropic capabilities (tool use, structured outputs, prompt caching, batch processing) into internal developer platforms Handle unglamorous production work: sandboxed execution, strict error handling, retries, observability, guardrails, and edge cases Own these systems after initial implementation: observe how they behave in real engineering workflows, investigate failures and incorrect behaviour, and improve the system based on operational evidence Partner with engineers across the org to identify automation opportunities and roll out agentic tools safely with human-in-the-loop review mechanisms WHAT WE'RE LOOKING FOR Strong software engineering background, with experience designing, building, and operating production systems, and strong hands-on experience with…