3 months ago
Tel Aviv-Yafo, IsraelSenior
Responsibilities
- Design, implement, and operate the retrieval system for a search vertical.
- Connect and tune the data pipeline from ingestion through relevance tuning.
- Build knowledge-graph and entity-resolution layers, including entity linking, named-entity recognition, ontologies, and graph databases.
- Develop structured-extraction pipelines over messy, unstructured domain data.
- Model fact confidence and staleness to assess freshness and trust before serving information.
- Define relevance and quality metrics and drive measurable improvements.
- Collaborate with crawling, indexing, and machine-learning teams to meet retrieval and ranking requirements.
- Enable safe experimentation with retrieval, ranking, and extraction strategies.
Requirements
- At least 6 years of software engineering experience, including some experience in search or information retrieval.
- Strong understanding of inverted indexes, BM25/TF-IDF, query understanding, ranking, and evaluation metrics such as nDCG, MRR, and recall@k.
- Experience with vector and hybrid retrieval, approximate nearest neighbor search, dense and sparse fusion, and embedding models.
- Experience building structured extraction pipelines over messy or unstructured domain data.
- Fluency in Python and comfort with systems-level performance work.
- Experience with knowledge graphs, entity resolution, entity linking, named-entity recognition, graph databases such as Neo4j, ontologies, or schema design is advantageous.
- Experience owning relevance or ranking for a real product and improving it against information-retrieval metrics is advantageous.
- Experience with data quality, truth discovery, or systems that assess information trustworthiness is advantageous.
- Published work on information retrieval, ranking, or knowledge graphs is advantageous.
- Applicants must be authorized to work in the country where they apply and provide proof of employment eligibility.
Benefits
- Competitive compensation
- Career growth and learning opportunities
- Flexibility and ownership
- Collaborative and innovative culture
- Opportunity to work on impactful AI projects
- International environment and talented teams
About Nebius
Nebius builds a full-stack AI cloud offering GPU compute, storage, and tools for training and deploying ML models for startups, enterprises, and research labs. It sells consumption-based cloud infrastructure (IaaS/PaaS) and managed services tailored to generative AI workloads, including large-scale model training and inference. The company is headquartered in Amsterdam and operates as an independent provider.