DATA SCIENTIST

THE POSITION

We're looking for a Senior Data Scientist to join a leading international media and information services organisation focused on building large-scale search and content discovery solutions.

In this role, you will join the Search team to improve an existing Hybrid Search platform that powers discovery across massive photo and video archives. You will design, prototype and optimise search algorithms, retrieval pipelines and query routing strategies to improve search quality, relevance and performance.

This is an excellent opportunity for a Data Scientist with strong experience in Information Retrieval, Semantic Search and Machine Learning, who enjoys solving complex search problems at scale while working closely with software engineers and product stakeholders.

RESPONSIBILITIES:

• Design, prototype and evaluate improvements to an existing Hybrid Search platform serving large-scale multimedia content.

• Develop and optimise search algorithms focused on semantic retrieval, ranking quality and relevance.

• Design and evaluate query classification and routing strategies — segmenting search queries by type and intent, and directing them through different parts of the retrieval algorithm.

• Experiment with embeddings, similarity search and retrieval methodologies to maximise search quality.

• Build prototypes and experiments using Python and Jupyter Notebooks, presenting different technical approaches and recommendations.

• Analyse search quality, diagnose which stage of the retrieval pipeline is under performing, and propose data-driven improvements

• Collaborate closely with engineering teams to transition validated solutions into production systems.

• Work with cross-functional stakeholders to iterate on search quality through experimentation, feedback and continuous optimisation.

• Design post-retrieval reranking and elimination strategies — deciding not only how results are ordered, but what should not be returned at all.

• Present technical findings and recommendations to both technical and non-technical audiences.

TECHNICAL REQUIREMENTS:

Must Have:

• 3+ years of professional experience as a Data Scientist or Machine Learning Engineer working on production systems.

• Strong Python skills, including experience with Jupyter Notebooks and data science libraries such as NumPy and Pandas.

• Strong understanding of Machine Learning fundamentals and NLP techniques.

• Hands-on experience with Semantic Search and Information Retrieval.

• Experience working with Embeddings and understanding different embedding spaces and similarity search techniques.

• Experience configuring and tuning Hybrid Search solutions — including how lexical and semantic signals are combined and weighted.

• Strong experience with Elasticsearch, including:

• BM25

• Relevance tuning

• Hybrid Retrieval

• Search optimization

• Experience working with rerankers, cross-encoders or similar retrieval optimisation techniques and post-retrieval filtering, thresholding or deduplication.

• Experience tuning search quality across datasets at the scale of tens of millions of documents or assets.

• Experience evaluating model performance and improving search quality through experimentation.

• Advanced English (B2+/C1).

Nice to Have:

• Experience searching multimedia content (images and videos).

• Experience with SageMaker.

• Familiarity with Retrieval Pipelines.

• Exposure to large-scale distributed search systems.

ABOUT YOU:

• Strategic, pragmatic, analytical, and technical thinking.

• Highly organised, ability to prioritise tasks and detail-oriented.

• Exceptional judgment, tact, and decision-making ability.

• Flexibility to adjust to multiple demands, shifting priorities, ambiguity, and rapid change.

• Outstanding management and interpersonal skills.