Hi! We're Extend, and we're helping companies deploy in-house AI agents for processing unstructured data. Extend is used in production at companies like Brex, Opendoor, Checkr, Vendr, and more. Our customers use our platform to build, deploy, and monitor intelligent data processing agents to turn their mountains of unstructured data (documents, PDFs, emails, images) → insights, customer NPS, operational efficiency, or new product initiatives.

We're powering mission-critical data processing at companies where if we get things wrong, there are real world impacts (e.g. missed payments, people can't move into homes on time).

Here's a few of the complex technical problems we're working on:

• How do we enable enterprises to deploy AI agents into production with confidence?
• How do we handle never before seen edge cases in customer data?
• How do we build a self-correcting system that automatically gets better over time?
• How do we enable non-technical domain experts to train AI agents with their expertise & business logic?
• How do we help customers make tradeoffs between latency, cost, and performance?
• How do we build reliable systems that can process large data streams in real-time?

Team

We're a small team of 5 that's fully in-person in NYC. Our backers include Homebrew, Innovation Endeavors, Character, and angels from OpenAI, Brex, Airbnb, Newfront, and more.

Extend is enabling enterprises to deploy in-house AI agents for processing unstructured data. As an AI Engineer at Extend, you’ll design novel techniques, systems, and human ↔ AI interfaces for building LLM agents that operate on complex data streams.

We’re looking to hire engineers who think creatively about problems, keep up to date on the latest in AI research, push for real-world customer impact (not only theory), and are excited about empowering organizations with AI.

Impact

We're powering mission-critical data processing at companies where if we get things wrong, there are real world impacts (e.g. missed payments, people can't move into homes on time).

Here's a few of the complex problems you’ll be working on:

• How do we build a self-correcting system that automatically gets better over time?
• How do we enable non-technical domain experts to train AI agents with their expertise & business logic?
• How do we deploy non-deterministic AI into mission-critical flows?
• How do we help customers make tradeoffs between latency, cost, and performance?

Role

• Design novel LLM techniques for increasing the complexity of use cases and data streams that Extend can be applied to
• Monitor existing agents in production, understand what’s working well (and what isn’t), and run experiments to solve those issues
• Implement the best human ↔ AI interfaces for designing data processing agents. We are building a new territory of UX that previously did not exist. It’s up to us to discover and implement new patterns that work for our users.
• Have complete ownership over the work you do — as a founding team member, you’ll have the opportunity to truly own large areas of product and engineering and have direct relationship with customers.
• Work directly with the CEO, CTO, and other founding members and help build out our team.

We view code as a tool to solving customer problems, and as such, prefer to keep our stack as simple as possible.

• Next.JS frontend
• Node backend
• Typescript everywhere
• Postgres
• Redis
• LLMs from OpenAI, Anthropic, and fine-tuned open source models