Principal Machine Learning Scientist
HybridLondon, England, United Kingdom
Job Summary
Lead the technical roadmap for Search, Retrieval, Ranking, and Recommendation systems within the Trips vertical by translating business goals into scalable ML architectures. Design, prototype, and deploy next-generation models utilizing sequential recommenders, deep multi-task frameworks, and graph neural networks to process billions of data points in real-time. Mentor senior and mid-level scientists while driving best practices for MLOps, rigorous A/B testing, and code quality across production-grade engineering teams. Partner with Product Managers and Engineering Leads to optimize multi-objective business outcomes like user engagement and booking conversion. This high-impact role bridges cutting-edge AI research with production systems to power the core discovery engine for millions of travelers.
Required Qualifications
- Ph.D. or Master's degree in Computer Science, Machine Learning, Statistics, or a highly quantitative field
- 8+ years of industry experience developing and deploying large-scale ML models in a production environment
- Proven track record of shipping systems at the scale of millions of active users
- Practical experience with Multi-Task Learning (MTL), Multi-gate Mixture-of-Experts (MMoE), or similar architectures optimized for multi-objective optimization
- Hands-on experience building sequential recommendation systems that capture real-time user session dynamics and long-term historical preferences
- Deep understanding of embedding generation, deep semantic retrieval, and multi-modal representation learning
- Mastery of Python and deep learning frameworks (TensorFlow, Pytorch)
- Hands-on experience with distributed computing (Spark, Ray) and cloud infrastructure (AWS/GCP)
Desired Qualifications
- Strong experience applying GNNs, knowledge graphs, or graph embeddings to map complex relations between travel entities (e.g., users, destinations, itineraries, points of interest)
- Familiarity with Agentic AI frameworks, LLM-driven reasoning, or autonomous planning agents to enhance conversational search and automated itinerary generation
- Experience working in E-commerce, Travel Tech, or Two-sided Marketplaces, specifically handling non-linear user journeys and highly constrained inventory (e.g., hotel availability, tour timings)
- A strong track record of academic or industry contributions, including publications in top-tier AI/IR conferences (e.g., SIGIR, KDD, RecSys, NeurIPS) or open-source ML contributions
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.