Senior Data Scientist - Conversational & Agentic AI

Location: London (Hybrid)

Swap 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.

• Agentic System Design & Multi-Agent Architecture: Design sophisticated AI agent ecosystems that autonomously handle complex e-commerce workflows.
• Conversational Flow & Agent Orchestration: Develop chat flows that guide users through e-commerce discovery, advice, and purchase journeys whilst managing handoffs between specialised agents with natural conversation transitions. 
• Prompt Engineering & Agent Optimisation: Develop and optimise prompts for both conversational AI and autonomous agents, implementing few-shot learning patterns, chain-of-thought reasoning, tool use, and structured output generation for multi-step agentic workflows.
• Fine-tune LLMs for Agentic Applications: Fine-tune language models for optimising both conversational flows and autonomous agent decision-making using techniques like LoRA, QLoRA, and full fine-tuning on e-commerce datasets with Vertex AI Training and frameworks such as Axolotl, Unsloth, or DeepSpeed.
• Design Agentic Quality Metrics: Create robust metrics to track user engagement, task completion rates, agent performance, multi-agent coordination effectiveness, and business outcomes.
• Build Predictive Models: Develop user behaviour prediction, conversation outcome forecasting, intent classification, agent performance prediction, and recommendation systems using scikit-learn, XGBoost, LightGBM, and Google Cloud AutoML.

• 4+ years in data science specialising in NLP, conversational AI, and agentic systems.
• Conversational & Agentic AI: Expert experience designing chat flows, dialogue systems, autonomous AI agents, multi-agent architectures, and advanced prompt optimisation including few-shot learning, chain-of-thought reasoning, tool use, and comprehensive AI agent development and evaluation.
• Advanced ML & LLMs: Expert proficiency in PyTorch, TensorFlow, Hugging Face, and fine-tuning techniques such as LoRA, QLoRA, or RLHF using Vertex AI Training and tools such as Axolotl or Unsloth.
• Data & Analytics: SQL experience, experimental design, and A/B testing, ideally with Google Analytics and Vertex AI.
• MLOps & Domain Knowledge: Production experience with Vertex AI Pipelines, MLflow, aWeights & Biases or similar platforms. Advanced Python skills and experience with agent frameworks and orchestration tools.

• A truly global team. Swap operates across time zones, markets, and currencies.
• Work with modern tech (AI-powered systems, cross-border APIs, advanced analytics).
• Autonomy with high impact. Your decisions will shape the backbone of ecommerce infrastructure for years to come.
• Equity, ownership, and career growth. We're scaling fast, and we want you on the journey.

• 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.