Machine Learning Engineer, Ranking & Retrieval

Role overview Build and operate machine learning systems that help a mobile communication product retrieve relevant context and personalize user experiences. The work spans model development, evaluation, deployment, and production monitoring, with a focus on delivering useful results while balancing quality, speed, cost, and reliability.

Responsibilities - Develop classification, retrieval, ranking, recommendation, and personalization models. - Improve search relevance with embeddings, hybrid retrieval, and reranking approaches. - Create datasets, evaluation pipelines, and metrics to measure quality and catch regressions. - Train, fine-tune, and deploy models through production ML workflows. - Monitor deployed systems, investigate issues, and use evaluation results and user feedback to guide improvements. - Tune models and inference systems for accuracy, precision, latency, and computational cost.

Requirements - At least three years of machine learning engineering experience, including production deployments. - Strong Python skills and experience with PyTorch or JAX. - Understanding of ML algorithms, training methods, and model evaluation. - Experience with classification, ranking, retrieval, recommendation, or personalization. - Familiarity with embeddings, vector search, or information retrieval systems. - Experience building data pipelines, training workflows, and inference services. - Ability to evaluate model quality through relevant metrics and experimentation, and to reason about performance trade-offs.

Nice to have - Experience with transformers, language-model fine-tuning, or embedding models. - Familiarity with retrieval evaluation, hybrid search, or reranking. - Consumer product recommendation or personalization experience. - Experience with large-scale training or inference infrastructure.