Responsibilities
- Assist in running experiments to enhance search performance using improved models, data strategies, and evaluation systems, with mentorship from experienced engineers.
- Develop and integrate components within the search infrastructure and modeling pipeline, such as retrieval, ranking, and classification systems.
- Train and assess models, including those based on large language models, for use in retrieval, ranking, and classification workflows.
- Support the scalable and efficient deployment and ongoing monitoring of search and ranking models in production.
- Contribute to the development and refinement of retrieval-augmented generation (RAG) pipelines for answer synthesis and context grounding.
- Work alongside Data, AI, Infrastructure, and Product teams to accelerate delivery and gain experience in real-world machine learning operations.
Work Arrangement
On-site — London
Other
Internship program: 12 - 24 weeks, full-time, in-person in the London office.