Thomson Reuters logo
Thomson ReutersPosted 1 month ago

Lead Applied Scientist, Search & Information Retrieval

$147,600–$274,200 year

On-siteToronto, Ontario, Canada or New York, United States

Full TimeSenior LevelDoctorate Or Professional DegreeEnterprise

Job Summary

Design and deploy large-scale search architectures supporting legal, tax, and enterprise content collections for Westlaw, Practical Law, and CoCounsel. Build and optimize ingestion pipelines that analyze and enrich documents, while developing ranking and re-ranking systems using traditional IR techniques and modern LLM-based approaches. Improve retrieval quality through semantic search, hybrid retrieval, and query understanding, and establish evaluation frameworks for relevance and end-user outcomes. Lead technical decisions on indexing strategies and partner with engineering teams to deliver scalable, reliable services. Mentor applied scientists and contribute to senior leadership strategy on search and AI initiatives.

Required Qualifications

  • PhD in Computer Science, Information Retrieval, AI, Machine Learning, NLP, or a related field
  • 8+ years of industry experience building production search, information retrieval, ranking, or recommendation systems
  • Publications at SIGIR, ACL, EMNLP, NeurIPS, ICLR, KDD, WWW, or equivalent venues
  • Strong production Python skills and experience with PyTorch, Hugging Face Transformers, and distributed model development
  • Hands-on production depth required in: Search engine architecture, indexing systems, and ingestion pipelines
  • Hands-on production depth required in: Ranking and re-ranking systems rather than solely consuming search technologies
  • Hands-on production depth required in: Information retrieval, semantic retrieval, hybrid retrieval, and vector search architectures
  • Hands-on production depth required in: Query understanding, relevance optimization, and search evaluation methodologies
  • Hands-on production depth required in: Retrieval systems supporting large collections of text-rich content
  • Hands-on production depth required in: LLM-enhanced retrieval, RAG architectures, and retrieval optimization
  • Hands-on production depth required in: End-to-end measurement and evaluation of search quality and user outcomes

Desired Qualifications

  • Experience with legal, regulatory, tax, scientific, or other text-heavy domains
  • Building retrieval systems over large enterprise knowledge repositories
  • Experience with Elasticsearch, OpenSearch, Solr, Vespa, or similar search technologies
  • API platform development and self-service search platforms
  • Agentic AI systems that incorporate retrieval capabilities
  • AzureML or AWS SageMaker
  • Experience building systems that combine search, retrieval, and document understanding capabilities

Hiring someone like this?

Get your role in front of qualified candidates on Sorce.

Get started

Apply to this job in one click with Sorce

Apply on Sorce