Location: London (Hybrid)
About SwapSwap is the infrastructure behind modern agentic commerce. The only AI-native platform connecting backend operations with a forward-thinking storefront experience.
Built for brands that want to sell anything - anywhere, Swap centralizes global operations, powers intelligent workflows, and unlocks margin-protecting decisions with real-time data and capability. Our products span cross-border, tax, returns, demand planning, and our next-generation agentic storefront, giving merchants full transparency and the ability to act with confidence.
At Swap, we’re building a culture that values clarity, creativity, and shared ownership as we redefine how global commerce works.
About the RoleWe are seeking a Senior Data Scientist to develop and evaluate intelligent autonomous AI agents for B2B analytics and operational workflows. You’ll engineer robust systems that enable agents to autonomously analyse data, generate insights, execute operational tasks, and orchestrate complex business workflows. You’ll work across analytical and operational workflows, designing multi-agent ecosystems, building evaluation frameworks, and ensuring production reliability for complex agentic systems.
Key responsibilitiesAgentic System Design & Multi-Agent Architecture: Design AI agent ecosystems that autonomously handle analytical and operational workflows including data exploration, insight generation, process automation, and cross-functional coordination.
Analytical & Operational Workflow Design: Develop agent systems that autonomously navigate data discovery, hypothesis testing, insight delivery, and operational task execution whilst managing handoffs between specialised agents (SQL, visualisation, statistical analysis, workflow automation) with seamless transitions.
Prompt Engineering & Agent Optimisation: Develop and optimise prompts for autonomous agents, implementing few-shot learning, chain-of-thought reasoning, tool use, and structured output generation for multi-step analytical and operational workflows.
Comprehensive Evaluation Frameworks: Build evaluation systems measuring analytical accuracy, operational task success, agent reliability, and coordination effectiveness. Develop automated testing suites, benchmark datasets, and continuous production monitoring.
Agent Performance Analysis: Create metrics and dashboards tracking query success rates, analytical correctness, task completion, error patterns, and business value. Conduct systematic A/B testing and comparative evaluations.
Production Engineering & Reliability: Build scalable, reliable agent systems with error handling, fallback mechanisms, logging, tracing, and debugging tools for complex multi-agent interactions.
4+ years in data science or ML engineering specialising in NLP, LLM systems, and agentic architectures.
Analytical & Agentic AI: Expert designing autonomous AI agents for data analysis and operational workflows, multi-agent architectures, SQL generation, and advanced prompt optimisation including few-shot learning, chain-of-thought reasoning, and tool use.
Evaluation & Experimentation: Strong experimental design, A/B testing, metrics development, and evaluation frameworks for LLM-based systems with automated and human evaluation methods.
Data & Analytics: Strong SQL experience with business intelligence platforms, data warehousing, and analytics tools.
Engineering & Production: Production experience with ML platforms (Vertex AI, MLflow, Weights & Biases), agent frameworks, and orchestration tools. Advanced Python with focus on reliable, scalable systems, monitoring, and observability.
Competitive base salary
Stock options in a high-growth startup
Competitive PTO with public holidays additional
Private Health
Pension
Wellness benefits
Breakfast Mondays
We embrace diversity and equality in a serious way. We are committed to building a team with a variety of backgrounds, skills, and views. The more inclusive we are, the better our work will be. Creating a culture of equality isn't just the right thing to do; it's also the smart thing.
