Search Relevance Engineer (Remote — Worldwide)

Join Glean as a Search Relevance Engineer to redefine how knowledge is discovered within the enterprise. You will work at the intersection of traditional information retrieval and cutting-edge GenAI to ensure employees find exactly what they need across hundreds of SaaS applications. Your work will directly impact the precision of our RAG pipeline, powering the 'magical' search experience that saves thousands of hours for teams worldwide.

- Design and implement state-of-the-art ranking algorithms that combine lexical and semantic signals. - Optimize the retrieval stage of our RAG (Retrieval-Augmented Generation) pipeline to improve LLM accuracy. - Develop and maintain evaluation frameworks to measure search relevance across diverse enterprise datasets. - Collaborate with the infrastructure team to scale search indices containing billions of documents. - Fine-tune embedding models to capture domain-specific jargon and organizational context. - Implement personalized search features that account for user permissions and activity signals. - Stay current with AI research to integrate new techniques like cross-encoders and rerankers.

- 5+ years of software engineering experience with a focus on Information Retrieval or NLP. - Proven track record of shipping production-grade ranking models or search heuristics. - Deep understanding of vector databases, embedding models, and hybrid search techniques. - Experience evaluating and fine-tuning Large Language Models (LLMs) for search-related tasks. - Proficiency in Python, Go, or Java within a distributed systems environment. - Strong analytical skills with experience in A/B testing and search quality metrics (NDCG, MRR). - Ability to work autonomously in a distributed, remote-first global team.

Equity, healthcare, wellness stipend.