Staff AI Engineer

Responsibilities

In this role, you will lead the design, development, and optimization of intelligent search systems that leverage machine learning at their core. You’ll be responsible for building end-to-end retrieval pipelines that incorporate advanced techniques in query understanding, ranking, and entity recognition.

The ideal candidate combines deep expertise in information retrieval and search relevance with hands-on experience applying machine learning to real-world search problems at scale.

• Lead the development of advanced query understanding systems that parse natural language, resolve ambiguity, and infer user intent
• Design and deploy learning-to-rank models that optimize relevance using behavioral signals, embeddings, and structured feedback
• Build and scale robust Entity Recognition pipelines that enhance document understanding, enable contextual disambiguation, and support entity-aware retrieval
• Architect next-gen search infrastructure capable of supporting highly dynamic document corpora and real-time indexing
• Create and maintain graph-based knowledge systems that enhance LLM capabilities through structured relationship data
• Drive improvements in query rewriting, intent classification, and semantic search, using both statistical and neural methods
• Own the design of evaluation frameworks for offline/online relevance testing, A/B experimentation, and continual model tuning
• Collaborate with product and applied research teams to translate user needs into data-informed search innovations

Requirements

• Bachelor's/Master's/PhD degree in Statistics, Mathematics, Computer Science, or another quantitative field
• 7+ years of backend engineering experience with 3+ years in search, information retrieval, or related fields
• Strong proficiency in Python
• Hands-on experience with search engines (Opensearch or Elasticsearch)
• Strong understanding of information retrieval concepts spanning traditional methods (TF-IDF, BM25) and modern neural search techniques (vector embeddings, transformer models)
• Experience with text processing, NLP, and relevance tuning
• Experience with relevance evaluation metrics (NDCG, MRR, MAP)
• Experience with large-scale distributed systems
• Proficiency in Knowledge Graph construction and optimization is a plus