Lead Applied Scientist, Search & Information Retrieval

Job Description

This role sits within the applied science function. You will own the design, development, and production deployment of large-scale search and information retrieval systems that power Westlaw, Practical Law, CoCounsel, and next-generation Thomson Reuters search experiences. The problems are real, the scale is large, and the expectation is shipped, reliable, measurable impact.

You will work across retrieval architectures, indexing pipelines, ranking and re-ranking systems, semantic retrieval, hybrid search, and retrieval optimization for complex legal, tax, and accounting content. Multiple product teams depend on what this function delivers.

Key Responsibilities

You hold a PhD in Computer Science, Information Retrieval, Machine Learning, NLP, or a related field, with 8+ years of post-degree industry experience building and deploying search and retrieval systems at scale. You have hands-on depth across indexing, retrieval, ranking, relevance evaluation, and production deployment.

You publish, you mentor, and you measure success by what ships and performs in production. You understand search beyond simply consuming vector databases or retrieval APIs. You have built, optimized, and evaluated search systems that solve real user problems.

Design and deploy search architectures supporting large-scale legal, tax, and enterprise content collections

Build and optimize ingestion pipelines that analyze, enrich, and prepare documents for retrieval

Develop ranking and re-ranking systems using both traditional IR techniques and modern LLM-based approaches

Improve retrieval quality through semantic retrieval, hybrid retrieval, query understanding, and relevance optimization

Design evaluation frameworks for retrieval performance, relevance, ranking quality, and end-user outcomes

Lead technical decisions around indexing strategies, retrieval architectures, ranking models, and search infrastructure

Partner with engineering teams to deliver scalable, reliable, and performant search services

Contribute to the development of self-service search platform capabilities used by internal product teams

Provide technical input to senior leadership on search, retrieval, and AI strategy

Mentor applied scientists and machine learning practitioners across the organization

Required Qualifications

PhD in Computer Science, Information Retrieval, AI, Machine Learning, NLP, or a related field preferred

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

Search engine architecture, indexing systems, and ingestion pipelines

Ranking and re-ranking systems rather than solely consuming search technologies

Information retrieval, semantic retrieval, hybrid retrieval, and vector search architectures

Query understanding, relevance optimization, and search evaluation methodologies

Retrieval systems supporting large collections of text-rich content

LLM-enhanced retrieval, RAG architectures, and retrieval optimization

End-to-end measurement and evaluation of search quality and user outcomes

Preferred 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