Senior Data Scientist - Conversational & Agentic AI

Swap; City Of London; On-site; GBP 70,000 - 90,000; Full time

Job summary

A leading software provider in London seeks an experienced Senior Data Scientist specializing in conversational AI and agentic systems. Responsibilities include designing AI workflows, optimizing models, and employing advanced machine learning techniques. Candidates should have over 4 years of experience in data science and expertise in tools like PyTorch and TensorFlow. Join a global team and impact e-commerce infrastructure.

Benefits

Autonomy with high impact

Equity and ownership

Career growth opportunities

Qualifications

• 4+ years in data science specialising in NLP, conversational AI, and agentic systems.
• Expert experience designing chat flows and dialogue systems.
• Proficiency in fine-tuning techniques and advanced ML tools.

Responsibilities

• Design sophisticated AI agent ecosystems.
• Develop chat flows for user engagement.
• Fine-tune language models for optimal performance.

Skills

Conversational & Agentic AI

Advanced ML & LLMs

Data & Analytics

MLOps & Domain Knowledge

Tools

PyTorch

TensorFlow

SQL

Vertex AI

Job description

Senior Data Scientist - Conversational & Agentic AI

Company

Say hello to the ecommerce OS.

Swap is a leading software provider dedicated to empowering e-commerce brands with innovative, data-driven solutions. Our cutting-edge platform helps online retailers optimise their operations, enhance customer experiences, and drive growth. We are committed to fostering a collaborative and inclusive work environment where creativity and innovation thrive.

We are seeking a Senior Data Scientist to develop machine learning models and analytics systems that power intelligent conversational AI and autonomous AI agents for e-commerce. You\'ll focus on model development, fine-tuning, measurement frameworks, and advanced ML techniques that enhance both conversational experiences and agentic capabilities.

What You\'ll Do

• 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.

Skills & Qualifications

• 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.

Why Join Us?

• 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.