Search Lead

This role.

Google Search is a generational technical achievement. Yet, the web is a terrible organization of the world’s information. If you were to find information on a person, you’d have to navigate 100s of pages (sometimes sequentially) and verify/assemble/correct/infer. When agents need to understand people, their social relationships, and professional lives, they can’t rely on the web.

Autumn is building a fundamentally new search index: on people rather than web pages. If the prospect of building Google from scratch does not excite you, this role is not a good fit.

As search lead, your goal is to design, build, and optimize our search engine. That means making decisions about what to index, how to represent it, how to keep it current, and how to rank results the harness can actually use. Concretely:

1. Search engine design. Design the schemas, ingestion, storage, and indexing systems that turn fragmented public information into useful, searchable entities. This is particularly tricky since you have to incorporate relationships (edges) between entities (nodes). Also, there is no universal schema that incorporates all attributes on all people. We are very very different from each other.
2. Identity resolution and freshness. Connect records about the same person or company, handle duplicates and conflicting attributes, and maintain updates as professional histories and relationships change.
3. Search infrastructure and optimization. Own index updates, query execution, serving APIs, and production observability. Improve latency and cost while preserving relevance and coverage.
4. Co-optimization for harness. This involves working closely with the Harness Lead to distinguish regressions/gaps from poor retrieval or poor tool use, and improve the system at the layer where it matters.

What we are looking for.

At Autumn, we strongly believe that successful people possess two traits: (1) agency, (2) ruthless prioritization. You must be able to will things into existence. This requires an incredible drive to make things happen quickly. You must also know the difference between what is urgent and what is important, and when to prioritize what. 

For this role specifically, we are looking for real experience in building large search systems (the bigger the better). You must also have deep infra + databases knowledge. You must also be comfortable owning the roadmap for the index: making architectural decisions and implementing them within reasonable timelines. We are also looking for work that demonstrates obsession; have you spent an insane amount of time or effort building or improving something?

Urgency.

All ambitious ideas come with a clock. We are in a rush to build a generational company. If you don’t feel this rush, this may not be the best fit for you.