Staff Software Engineer — Search Platform, Ingestion & Indexing
Core
Design, build, and operate the end-to-end document ingestion pipeline and search index management systems for a hybrid search engine powering human interfaces and autonomous AI agents.
Role type
Staff Software Engineer (Search Infrastructure)
Builds
High-throughput document ingestion pipelines, Vespa/OpenSearch index configurations, and model operationalization services.
Domain
Legal/Tax/Professional content search, Distributed Systems, AI/ML Infrastructure
Deliverable
production ML models | infrastructure
Required skills
Distributed stream processing (Kafka), Search engine internals (Vespa/OpenSearch), Python, AWS cloud services, Infrastructure as Code, System design, Operational ownership
Preferred skills
ML model operationalization, Agentic retrieval patterns, Online search analytics, Vector indexing, Protobuf schema design
Technologies
Kafka, Vespa, OpenSearch, Python, AWS (MSK, ECS, Lambda, DynamoDB), Terraform, Protobuf
Responsibilities
Design and own the end-to-end document ingestion pipeline architecture; Architect and implement pluggable pipeline components; Own the lifecycle of custom models integrated into the pipeline; Manage search engine layer configurations and zero-downtime index updates; Design ingestion infrastructure with agentic retrieval patterns; Build integration between ingestion pipeline and offline evaluation frameworks; Take full operational responsibility for infrastructure SLOs and on-call; Mentor senior and mid-level engineers.
Seniority
Staff, technical anchor & leadership
