Join Our Team as a Senior Data Scientist - Conversational & Agentic AILocation: London (Hybrid)About SwapAt Swap, we are at the forefront of revolutionizing agentic commerce with our innovative AI-native platform. We connect backend operations seamlessly with a modern storefront experience.Our platform is tailored for brands eager to expand their reach, enabling them to sell anything, anywhere. Swap consolidates global operations, enhances intelligent workflows, and empowers businesses to make informed decisions with real-time data. Our extensive product range includes solutions for cross-border transactions, tax management, returns, demand planning, and next-generation agentic storefronts, providing merchants with full transparency and confidence in their operations.We foster a company culture that values clarity, creativity, and shared ownership as we redefine the landscape of global commerce.About the RoleWe are looking for a Senior Data Scientist to spearhead the development and evaluation of intelligent autonomous AI agents focused on B2B analytics and operational workflows. You will be responsible for engineering sophisticated systems that enable agents to autonomously analyze data, generate actionable insights, execute operational tasks, and orchestrate complex business processes. Your role will involve working across analytical and operational workflows, designing multi-agent ecosystems, establishing evaluation frameworks, and ensuring the reliability of complex agentic systems in production.Key ResponsibilitiesAgentic System Design & Multi-Agent Architecture: Architect AI agent ecosystems capable of autonomously managing analytical and operational workflows, including data exploration, insight generation, process automation, and cross-functional coordination.Analytical & Operational Workflow Design: Create agent systems that proficiently navigate data discovery, hypothesis testing, insight delivery, and operational task execution, effectively managing transitions between specialized agents (SQL, visualization, statistical analysis, workflow automation).Prompt Engineering & Agent Optimization: Craft and refine prompts for autonomous agents, incorporating few-shot learning, chain-of-thought reasoning, tool usage, and structured output generation for multi-step analytical and operational workflows.Comprehensive Evaluation Frameworks: Develop evaluation systems that measure analytical accuracy, operational task success, agent reliability, and coordination effectiveness. Create automated testing suites, benchmark datasets, and continuous production monitoring protocols.Agent Performance Analysis: Conduct thorough analyses of agent performance to drive system improvements and enhance operational efficiency.
Jan 22, 2026