Data Scientist
Core
Design, develop, and optimize enterprise-scale search solutions using vector embeddings, neural models, and hybrid search systems.
Role type
Senior IC search engineer (semantic search)
Builds
Enterprise search products with hybrid keyword and vector capabilities
Domain
Search technology / Information retrieval
Deliverable
production ML models | product features
Required skills
Apache Solr, Lucene, vector embeddings, neural search models, Approximate Nearest Neighbor (ANN) algorithms, relevancy engineering, query analysis, field weighting, result tuning, quantitative metrics (NDCG, MRR, precision/recall), Python, SQL, C/C++, Java, Bash
Preferred skills
Elasticsearch, Big Data data engineering, statistical methods
Technologies
Apache Solr, Lucene, Elasticsearch, Python, SQL, C/C++, Java, Bash, R, Matlab
Responsibilities
Design and implement enterprise-scale search solutions; Develop and optimize semantic search capabilities using vector embeddings; Build custom indexers and indexing pipelines for vector embeddings; Implement and tune Approximate Nearest Neighbor (ANN) algorithms; Design and optimize similarity functions for various search use cases; Build hybrid search systems combining keyword and vector-based approaches; Conduct relevancy analysis using quantitative metrics and qualitative evaluation methods; Monitor search performance metrics and implement continuous improvements
Seniority
Senior, hands-on IC