SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Exa is an applied AI lab building a next-generation search engine powered by massive-scale infrastructure. The company crawls the entire web, trains state-of-the-art embedding models, and operates high-performance vector databases. Exa powers search for Cursor, Cognition, HubSpot, and over 400,000 developers, with $350M in funding from Lightspeed, Benchmark, and a16z.
The Knowledge Platform team builds Exa's knowledge engine, continuously synthesizing information from across the web into one of the world's largest open-domain knowledge graphs containing hundreds of billions of evidence-backed claims. The team focuses on construction pipelines (deciding what to trust) and retrieval engines (optimizing search performance).
In this role, you will own the query engine that searches hundreds of billions of claims across multiple retrieval backends, including distributed graph databases, vector indexes, full-text search, time-series, and geospatial indexes. This is greenfield work with massive scope—no off-the-shelf system exists to answer precise questions over hundreds of billions of evidence-backed claims at agent speed.
Key responsibilities:
- Own storage and indexing across backends: design data layout, partitioning, and indexes for graph, vector, full-text, time-series, and geospatial retrieval, with bulk snapshot builds and live ingest that maintain system availability.
- Design query planning: build cost-based planners using cardinality estimates to choose which backends to use for each question, in what order, and how to join results through traversals, retrievals, filters, and aggregations.
- Optimize for scale: serve thousands of queries per second, profile and reduce p50/p99 latency, memory, and cost per query under high concurrent load.
- Ensure consistency: manage eventual consistency as the graph receives both live updates and bulk snapshots, owning consistent snapshot promotion, ordered update application, and stable pagination across versions.
- Measure quality: implement end-to-end checks for every deployment, plus evals and metrics to detect incorrect results or missed findings.
REQUIREMENTS:
- Deep experience inside a distributed database, query engine, search engine, or storage system.
- Strong grasp of indexing, query planning and optimization, and storage formats.
- Solid understanding of distributed systems fundamentals: consensus, replication, sharding, and fault tolerance.
- Strong proficiency in a systems language (Go, Rust, or C++).
- Demonstrated ability to profile before optimizing, with shipped measured latency wins in production.
- Obsession with correctness, reliability, and data quality alongside scale.
BONUS QUALIFICATIONS:
- Experience with graph databases or combining vector, full-text, time-series, and geospatial retrieval.
- Background in compilers, query language design, or cost-based optimizers.
