Senior ML Engineer (Agentic Search)

Role overview

Build machine learning capabilities for a production search platform that helps AI systems find fresh, relevant information. The work spans retrieval, ranking, indexing, and evaluation, with a focus on serving high query volumes while balancing result quality, latency, and operating cost.

Responsibilities - Design, train, and deploy models for search relevance, retrieval, and reranking. - Develop embedding-based indexing and large-scale retrieval methods. - Build models that support web crawling, content selection, and content understanding. - Create quality metrics and evaluation pipelines for search performance. - Integrate models into production services and work with engineering partners on system design. - Experiment with current search and language-model techniques, assessing their impact on quality, speed, and cost.

Requirements - At least five years of software engineering or applied machine learning experience. - Strong programming ability in Python, Go, or C++. - Experience deploying machine learning models in production. - Practical experience with retrieval, ranking, recommendation, or a related machine learning problem. - Knowledge of machine learning and modern deep learning methods. - Experience with large-scale data systems, high-throughput workloads, and model evaluation. - A product-focused approach, strong problem-solving skills, and ability to work with a distributed team.

Nice to have - Experience with search engines or large-scale information retrieval. - Familiarity with embeddings, transformers, natural language processing, or language-model and agent-based systems. - Open-source contributions, technical publications, conference talks, or competitive machine learning experience.

Benefits and work setup The role offers competitive compensation, learning and career development, flexibility, and ownership. Work involves close collaboration across an international team on production systems.