The opportunity

We build agentic AI for intellectual property. Legal and IP teams use our software to reason across massive document sets, surface evidence, and produce litigation-grade work faster and more reliably. Intellectual property is one of the last durable moats, and we're at the very beginning of defining what great AI-native software for it looks like. We already work with leading IP firms and Fortune 500 companies.

About the role

You'll be one of the first hires outside the founding team. Your decisions will shape the product for years. You'll own the AI core of the product: multi-agent reasoning pipelines, retrieval over hundreds of millions of patents and scientific literature, and the evaluation systems that prove the output holds up for practitioners at top IP firms and Fortune 500 IP teams. These are problems without established patterns. You're building agentic software that patent lawyers actually trust to do substantive work, and you'll define what this category of product looks like.

What you will do

Architecture: Build and improve the multi-agent architecture powering invalidity search, infringement analysis, freedom to operate research, and more.
Ownership: Own the full lifecycle of features, from talking to customers about what they need to watching them use it in production.
Shipping: Push code to production daily. Your code reaches users in hours or days, not weeks.
Retrieval and evals: Build retrieval, reasoning, and evaluation systems that run autonomously over millions of documents with reliable, source-backed results.
Standards: Set the standards for how we build, evaluate, and ship AI systems as the team scales.

What we are looking for

Exceptional matters more than experienced. We care about what you can do, not how long you've been doing it.
Strong engineering fundamentals and a strong opinion about product.
You write software with and for AI agents, and you've shipped agentic systems to production before. You know how to make LLMs reliable through context engineering, retrieval, and evals.
You can take an AI capability from sketch to production on your own: write the specs, design the evals, wire the agent pipeline, and deploy it.
Comfortable across Python and TypeScript, with enough experience with infrastructure (vector databases, distributed compute, cloud orchestration) that none of it slows you down.

Plus: experience navigating enterprise requirements such as SOC 2, data residency, and access controls.

What we offer

Competitive salary and equity
Unlimited Claude Code: experiment with AI-assisted workflows, prototypes, and automations from day one
A front-row seat: you'll be shaping the foundation of the business

Logistics

Location: Stockholm, Sweden (on-site)
Type: Full-time, Engineering

We are an equal opportunities employer and welcome applications from all qualified candidates, regardless of age, disability, gender, gender identity, sexual orientation, ethnicity, religion, or background. Selection is based solely on suitability for the position.