Machine Learning Engineer, Ranking & Retrieval

Role overview Build and improve machine learning systems that help an AI-powered communication product find relevant information and tailor results to users. The work spans model development, search and retrieval, evaluation, and production deployment, with attention to quality, speed, and operating cost.

Responsibilities - Develop models for classification, ranking, retrieval, recommendations, and personalisation. - Improve search relevance and context retrieval using embeddings, vector search, hybrid methods, and reranking. - Build datasets, evaluation pipelines, and metrics to measure model quality and catch regressions. - Train, fine-tune, deploy, and monitor models through production ML workflows. - Investigate production issues and use evaluation results and user feedback to guide improvements. - Balance accuracy and precision against latency, inference cost, and reliability.

Requirements - At least 3 years of machine learning engineering experience, including production model deployment. - Strong Python skills and practical experience with PyTorch or JAX. - Understanding of machine learning algorithms, training, and evaluation. - Experience with classification, ranking, retrieval, recommendation, or personalisation models. - Familiarity with embeddings, vector search, or information retrieval systems. - Experience building data pipelines, training workflows, and inference services, and evaluating models with relevant metrics and experiments.

Nice to have - Experience with transformers, large language model fine-tuning, or embedding models. - Background in hybrid search, reranking, or retrieval evaluation. - Experience with consumer recommendation or personalisation systems, or large-scale ML infrastructure.