Staff Software Engineer, Search Infrastructure

About the Role Moveworks is seeking an engineer to architect and operate a scalable, agent-native search infrastructure that enables locating, searching, discovering, and recommending resources across enterprise data. You will build the infrastructural substrate beneath the agentic search platform and own end-to-end responsibilities for indexing, ingestion, enrichment, and entity intelligence that give content context. What You'll Do

• Build and own the infrastructural substrate beneath the agentic search platform, spanning the index engine, ingestion/enrichment pipeline, and the entity/identity/feature intelligence that gives content context.
• Keep index-time enrichments aligned with query-time expectations to enable consistent retrieval, ranking, and reasoning foundations.
• Build and operate hybrid indexing at scale across large clusters, including keyword-based sparse-vector indices, embedding-based semantic indices, and semantic-ID indexing driven by next-token prediction.
• Own the full index lifecycle and expose clean contracts to search primitives and recipes used by agents on top of the corpus.
• Design and run high-throughput ingestion and enrichment pipelines to produce a multi-representation, permission-aware corpus at index time; orchestrate parsing, chunking, embedding, entity resolution, and access control, evolving them for new agentic use cases.
• Build and operate multi-modal indexing across text, structured content, diagrams, images, audio, and video, representing each modality for unified retrievability.
• Contribute to a knowledge graph that resolves entities across enterprise data sources, linking tickets, files, and people through canonical relationships.
• Improve performance, scalability, and observability of search (latency, throughput, cluster health); apply techniques such as vector quantization to balance quality, retrieval performance, and storage cost.
• Own search infrastructure end to end, from intake and design through rollout and ongoing operations, and help shape the search roadmap. What We're Looking For
• Experience building and operating large-scale search/information-retrieval systems and knowledge graphs.
• Proficiency with index design, multi-modal indexing, and embedding-based retrieval.
• Strong background in data ingestion, enrichment pipelines, parsing/chunking, and entity resolution with access-control considerations.
• Familiarity with distributed systems, observability, performance tuning, and scalable architectures.
• Ability to collaborate with product teams to shape roadmaps and agent-based use cases. Nice to Have
• Experience with next-token-prediction based indexing, vector quantization, and semantic-ID indexing.
• Experience with enterprise data sources and permissions-aware data governance.