Machine Learning Engineer, Ranking & Retrieval

Role overview Join a Search team building the retrieval and ranking systems that power large-scale, AI-driven search experiences. This role owns the full machine learning lifecycle for ranking models and retrieval infrastructure across a multi-tenant platform serving millions of users, where permission-aware results are critical. It is a remote, senior-level engineering position focused on production ML systems at scale.

Responsibilities - Train, deploy, and serve ranking models in production, owning the full ML lifecycle end to end - Engineer ranker features, build training pipelines, and develop offline evaluation frameworks - Design and scale hybrid retrieval that combines lexical and vector search, including HNSW with disk offloading - Run embedding inference at billions-of-documents scale - Improve query understanding through intent modeling and query expansion - Build permissions-aware retrieval that respects multi-tenant boundaries - Create measurement frameworks to evaluate and continuously improve search quality - Collaborate with Search Infrastructure, AI, and backend teams to integrate ranking improvements across the platform

Requirements - Bachelor's degree in Computer Science, Machine Learning, or a related field - 5+ years of ML engineering experience with a focus on ranking, retrieval, or information retrieval - Demonstrated ownership of the full ML lifecycle, from training through production deployment and serving - Hands-on experience training ranker models, including feature engineering, pipeline development, and offline evaluation - Experience building hybrid retrieval systems that combine lexical and vector approaches - Experience running embedding inference at large scale - Strong fundamentals in query understanding, including intent modeling and query expansion

Nice to have - Permission-aware retrieval and multi-tenancy experience - Indexing large-scale, user-generated content rather than small or static datasets - Hands-on experience with OpenSearch or Elasticsearch - Familiarity with sharding, index management, and real-time ingestion at scale - Background in NLP, semantic search, or agentic retrieval - Experience with TypeScript in backend systems

Benefits and work setup - Remote-first work setup - Engineering and product visa sponsorship considered based on business needs (not guaranteed)