Role
As a Senior Machine Learning Engineer in the ML Recall team, you help shape the retrieval layer of a large-scale e-commerce search engine used by hundreds of millions of shoppers worldwide.
You build and improve retrieval systems that ensure relevant products are shown for queries across languages, markets and domains. Your work covers dense and sparse retrieval, query understanding, visual search and multimodal solutions. You work with modern deep learning and transformer-based models, balancing relevance, generalisation and latency at the millisecond level.
The role offers ample opportunities for research and experimentation, including testing new architectures and approaches on live traffic. You own models end-to-end: from problem definition and experimentation to deployment, A/B testing and measurable impact. You will join a highly technical, remote-first environment in which your work directly influences search quality, user experience and business performance.
Responsibilities
- Developing and optimising modern search retrieval systems with dense and sparse models, query understanding and other machine learning techniques.
- Building solutions that balance retrieval quality and strict latency requirements, so that relevant products are returned within milliseconds.
- Developing end-to-end visual and multimodal search capabilities, including image search, visual recommendations and "shop the look" experiences.
- Training, fine-tuning, evaluating, deploying and continuously improving deep learning models that are used across multiple products and teams.
- Experimenting with new model architectures, retrieval approaches and techniques, and validating their effectiveness through A/B testing and live traffic experiments.
- Tackling complex measurement challenges in search recall by developing reliable ground truth and evaluation methodologies for products that might otherwise be missed entirely.
- Designing models that generalise across 40+ languages and 20+ domains without relying on customer-specific rules or overrides.
- Taking end-to-end ownership of machine learning initiatives, from problem framing and research to production rollout and ongoing optimisation.
- Collaborating with other engineering and machine learning teams whose products build on the models and capabilities you develop.
Required