Senior AI Scientist — Agentic Modeling & Production Agents

Booking Holdings, Inc.; Amsterdam; Hybrid; EUR 110,000 - 170,000; Full time

Benefits offered by this job

Hybrid working

Generous leave

Product discounts

Genius status

Job summary

Booking.com is seeking a Senior Machine Learning Scientist to advance the agentic platform, focusing on agent strategies, memory systems, and multi-agent patterns. You will work at the intersection of NLP research and production systems, delivering scalable capabilities across teams.

We value deep expertise in Python, ML frameworks, LLMs, and retrieval systems, with a track record of publishing or open-source contributions. The role combines research rigor with high-impact product delivery.

Qualifications

• Advanced knowledge in NLP, LLM-based systems and agent architectures.
• Ensure end-to-end research to production.
• Experience with evaluation and optimization of model-based systems.
• MSc + 6 years or PhD + 4 years in a quantitative field; strong ML problem solving.
• Proficiency in Python and ML frameworks.

Responsibilities

• Research and develop advanced agent strategies and multi-step reasoning.
• Design context management and memory systems to personalize agent experiences.
• Implement multi-agent patterns enabling collaboration and task delegation.
• Lead systematic experimentation with model selection and prompt engineering.
• Collaborate with ML engineers to translate research into production-grade capabilities.
• Collaborate with product teams to translate business requirements into capabilities.

Skills

NLP

LLM architectures

Agentic AI

Tool use

Reasoning

RAG

Agent planning

Python

ML frameworks

LLM APIs

Retrieval systems

Education

MSc + 6 years

PhD + 4 years

Tools

Python

ML frameworks

LLM APIs

Retrieval systems

Job description

Booking.com is seeking a Senior Machine Learning Scientist to advance the agentic platform, focusing on agent strategies, memory systems, and multi-agent patterns. You will work at the intersection of NLP research and production systems, delivering scalable capabilities across teams.

We value deep expertise in Python, ML frameworks, LLMs, and retrieval systems, with a track record of publishing or open-source contributions. The role combines research rigor with high-impact product delivery.