Software Engineer, Knowledge Engine – Query Engine

Description

The company is an applied AI lab building a search engine. It crawls the entire web, trains embedding models to process what it finds, and runs vector databases to retrieve from them. It already powers search for Cursor, Cognition, HubSpot, and over 400,000 developers, and has raised $350m from Lightspeed, Benchmark, and a16z.

The long-term aim is perfect search over all of the world's information, well beyond Google. The work involves large-scale ML systems that will shape how AI systems take in information.

The Knowledge Platform team builds the company's knowledge engine. It continuously pulls information from across the web and other sources into one of the largest open-domain knowledge graphs, which holds hundreds of billions of evidence-backed claims. The team splits its work between construction pipelines, which decide what to trust, and retrieval engines, which decide how to search. The goal is to give agents accurate, complete answers to any factual question.

This is a greenfield project at large scale. No existing system answers precise questions over hundreds of billions of evidence-backed claims at agent speed, so the foundational choices are open. These include storage layout, indexing across engines, the query language, and the planner that routes work between them. Every query depends on these choices.

Responsibilities

• Own the query engine that searches hundreds of billions of claims across a distributed graph database and vector, full-text, time-series and geospatial indexes.
• Design data layout, partitioning and indexes for each backend, so bulk snapshot builds and live ingest run without taking the system down.
• Build a cost-based planner that uses cardinality estimates to pick the backends for each question, their order, and how to join results. Plans run as traversals, retrievals, filters and aggregations.
• Serve thousands of queries per second. Profile and reduce p50 and p99 latency, memory use and cost per query under heavy concurrent load, from on-disk layout through network fan-out.
• Control what a query can see while the graph converges. Live updates and bulk snapshots both feed it, and it is eventually consistent by design. Own consistent snapshot promotion, ordered application of live updates, and stable pagination across versions.
• Measure precision and completeness. Write the end-to-end checks every deployment must pass, and build evals and metrics that flag wrong results and missed ones.

Requirements

• You have worked deep inside a distributed database, query engine, search engine or storage system.
• You have a strong grasp of indexing, query planning and optimization, and storage formats.
• You understand distributed systems well, including consensus, replication, sharding and fault tolerance.
• You are strong in a systems language such as Go, Rust or C++.
• You profile before optimizing and have shipped measured latency improvements to production.
• You care about correctness, reliability and data quality as much as scale.
• Bonus: experience with graph databases, or with combining vector, full-text, time-series and geospatial retrieval.
• Bonus: experience with compilers, query language design or cost-based optimizers.
• Bonus example projects: a system that retrieves and reasons over everything known about any company or person; answering precise multi-hop questions over hundreds of billions of claims at thousands of QPS with interactive latency; a planner that picks the mix of graph, vector, full-text and geospatial retrieval for any question and proves the choice was right; making new knowledge queryable seconds after synthesis without ever serving an inconsistent result.

Conditions

Visa sponsorship is available for international candidates, including STEM OPT, OPT, H1B, O1 and E3. The company cannot guarantee a visa, but it has a strong record of sponsoring candidates from around the world, and after an offer it will work to secure one.

Benefits

• Premium healthcare covering medical, dental and vision.
• Fertility benefits.
• 16 weeks of fully paid parental leave for all new parents.
• A monthly wellness stipend for all employees.