Senior Machine Learning Scientist - Marketplace

Role Description:

At Booking.com, data drives our decisions. Technology is at our core and innovation is everywhere. But our company is more than datasets, lines of code or A/B tests. We’re the thrill of the first night in a new place. The excitement of the next morning. The friends you make. The journeys you take. The sights you see. And the food you sample. Through our products, partners and people, we can empower everyone to experience the world.

About the team:

This opening is for the Agentic Modeling Team within the Data & AI Marketplace department.

The Agentic Modeling team is responsible for enabling mission teams across Booking.com to build, deploy, and continuously improve production-grade AI agents — without requiring deep AI expertise. We provide a modular, configuration-driven platform where teams compose reusable building blocks — tools, memory, context management, agent strategies, and system prompts — into custom agents tailored to their domains. Our SDK and tooling support the full agent lifecycle: building, evaluating, optimizing, publishing, and iterating on agents that power the Connected Trip experience.

As a Senior Machine Learning Scientist, you will research, design, and develop the core AI capabilities that power our agentic platform — focusing on agent strategies, reasoning architectures, context management, memory systems, and multi-agent patterns. You will work at the intersection of LLM research and production systems, translating state-of-the-art techniques into reusable, scalable capabilities that teams across Booking.com can leverage through configuration.

Key Job Responsibilities and Duties:

• Research and develop advanced agent strategies - iterative planning, self-correction, multi-step reasoning, and conditional execution paths.
• Design and build context management and memory systems (session-level and long-term) that enable personalized, improving agent experiences.
• Research and implement multi-agent patterns - enabling specialized agents to collaborate, share context, and delegate sub-tasks.
• Help build systematic experimentation and optimization - model selection, strategy comparison, prompt engineering, and architecture decisions backed by quantitative analysis.
• Build reusable ML components that encode production best practices and are available to all teams through configuration.
• Collaborate closely with ML engineers to ensure research translates into production-grade capabilities with appropriate latency and reliability.
• Collaborate with cross-functional teams (product managers, mission teams, platform engineers) to translate business requirements into agent capabilities.

Qualifications & Skills:

• Advanced knowledge and experience in NLP, LLM-based systems, and agentic AI architectures - including tool use, reasoning, retrieval-augmented generation, and agent planning.
• Experience designing and building production agentic or conversational AI systems at scale.
• Experience with LLM evaluation and optimization - designing metrics and systematically improving model-based systems.
• Relevant work or academic experience (MSc + 6 years, or PhD + 4 years), applying Machine Learning to business problems.
• Masters degree, PhD or equivalent experience in a quantitative field (e.g., Computer Science, Artificial Intelligence, Mathematics, Physics, etc.).
• Experience designing and executing end-to-end R&D plans. Preferably evidenced by peer-reviewed publications, patents, or open-source contributions.
• Strong working knowledge of Python and ML/AI frameworks. Experience with LLM APIs and retrieval systems.
• Experience collaborating cross-functionally in the development of ML-powered products.
• Excellent English communication skills, both written and verbal.
• Successfully driving technical and people-related initiatives while communicating with stakeholders at all levels.
• Lead