12 days ago
Responsibilities
- Lead the development of advanced query understanding systems that parse natural language and infer user intent.
- Design and deploy learning-to-rank models that optimize relevance using behavioral signals.
- Build and scale robust Entity Recognition pipelines for enhanced document understanding.
- Architect next-gen search infrastructure for dynamic document corpora and real-time indexing.
- Create and maintain graph-based knowledge systems to enhance LLM capabilities.
- Drive improvements in query rewriting, intent classification, and semantic search.
- Own the design of evaluation frameworks for relevance testing and model tuning.
- Collaborate with product and research teams to translate user needs into search innovations.
- Produce clean, scalable code and influence system architecture across the relevance stack.
Requirements
- Bachelor's/Master's/PhD degree in Statistics, Mathematics, Computer Science, or a related field.
- 7+ years of backend engineering experience with 3+ years in search or information retrieval.
- Strong proficiency in Python.
- Hands-on experience with search engines like OpenSearch or Elasticsearch.
- Strong understanding of information retrieval concepts and modern neural search techniques.
- Experience with text processing, NLP, and relevance tuning.
- Familiarity with relevance evaluation metrics such as NDCG, MRR, and MAP.
- Experience with large-scale distributed systems.
- Proficiency in Knowledge Graph construction is a plus.
- Strong analytical and problem-solving skills.