Senior Staff Agentic Search Infrastructure Engineer - Moveworks

Description

The company is building the next generation of enterprise search infrastructure for AI agents, moving from product-specific search systems to a composable, agent-native platform. Agents and applications will use it to find, retrieve, reason over and recommend information from many kinds of enterprise data sources.

As a Senior Staff Engineer, you will be the technical owner of the foundational search infrastructure behind the agentic platform. You will shape the architecture, scale and evolution of core indexing and retrieval systems, working with the Search Ranking, ML, Platform and AI teams to ship production search features used across the company.

Responsibilities

• Lead the design, build and running of key search infrastructure, including indexing, ingestion pipelines, metadata enrichment and retrieval foundations for a growing set of AI agents.
• Set technical direction and make architecture decisions across several search infrastructure areas so the platform can handle future agent use cases and larger enterprise datasets.
• Act as the final technical authority for the full search lifecycle, from content ingestion through retrieval and ranking.
• Design and run large-scale hybrid indexing that combines sparse retrieval, dense vector search, semantic retrieval and newer indexing methods.
• Create clear abstractions and interfaces so ranking systems and agents can use search consistently across retrieval approaches.
• Push improvements in search quality, latency, scalability and cost across billions of indexed entities.
• Design high-throughput ingestion and enrichment pipelines that turn enterprise content into permission-aware representations for agents.
• Define how content is parsed, chunked, embedded, entity-extracted, enriched with metadata and access-controlled.
• Keep index-time representations consistent with query-time retrieval so agent reasoning has a dependable base.
• Lead the evolution of indexing and retrieval for text, structured data, images, diagrams, audio and video.
• Build unified frameworks that let agents find and reason across different content types through one retrieval experience.
• Work with ML and AI teams to move new multi-modal capabilities into production.
• Help design and evolve the enterprise knowledge graph linking people, content, tickets, documents, conversations and business entities.
• Lead work that improves entity resolution, relationship modeling and contextual understanding across the search platform.
• Own platform metrics for search latency, indexing throughput, retrieval quality, infrastructure efficiency and cluster health.
• Improve operations through observability, capacity planning, resiliency work and lifecycle management.
• Lead efforts to reduce infrastructure cost without losing retrieval performance at scale.
• Mentor engineers across the organization and provide technical leadership.
• Shape the roadmap and architecture through technical vision, design reviews and work with other teams.
• Align Search Infrastructure, Ranking, ML and Platform teams on solutions to hard engineering problems.
• Lead multi-quarter initiatives that cross teams and move the agentic search platform forward.

Requirements

• A BS or MS in Computer Science or a related technical field.
• 8 to 12+ years of industry experience building large-scale distributed systems, search platforms or data infrastructure.
• Hands-on depth with search technology such as Lucene, Elasticsearch, OpenSearch, Solr or similar retrieval systems.
• Solid experience designing and running distributed systems at scale, covering storage, indexing, serving and data processing.
• Experience building and scaling production systems that use vector search, embeddings, retrieval or AI-driven search.
• A record of leading complex technical work across teams and shaping architecture beyond your own team.
• Ability to combine technical depth with practical delivery and operational discipline.
• Preferred: a PhD.
• Preferred: experience with information retrieval, ranking, recommendation or AI-powered search platforms.
• Preferred: experience with knowledge graphs, entity resolution or enterprise data modeling.
• Preferred: familiarity with dense retrieval, RAG architectures, hybrid search and semantic indexing.
• Preferred: experience running large search clusters and performance-sensitive distributed infrastructure.
• Preferred: experience working with ML or AI platform teams to put intelligent retrieval into production.
• Preferred: comfort collaborating in a highly engaged, in-person engineering culture.
• Preferred: strong communication and a record of influencing across organizational boundaries.
• Preferred: enthusiasm for foundational infrastructure problems that enable the next generation of AI agent experiences.

Conditions

Base pay for this role in the applicable location is $190,900 to $334,100. Equity (where applicable) and variable or incentive pay are also offered.

Base pay is a guideline. Total compensation depends on qualifications, skill level, competencies and work location, and pay is based on the location where the role sits and may change with it.

Sales roles generally carry an On Target Earnings incentive structure; this note is standard company text.

Work persona is flexible, remote or required in office, assigned by the nature of the work and the employee's work location.

The company may use a third-party service to check the distance between your primary residence and the nearest office when deciding persona eligibility.

Benefits

• Health plans, including flexible spending accounts.
• 401(k) plan with company match.
• Employee stock purchase plan (ESPP).
• Matching donations.
• Flexible time away plan.
• Family leave programs.