Sanna is building a new kind of accounting firm, designed from the ground up for a world where AI handles much of the manual work that has defined the industry for decades.

We combine accounting expertise with software and AI to deliver better service at a lower cost. Founded in 2025, we already serve more than 2,000 companies. We're starting with holding companies in Norway, expanding into operating companies, and building for international scale from day one.

We're a small, ambitious team based in Oslo and Stockholm. Engineers work closely with accounting professionals and clients, with real ownership over what we build and how it performs.

We're building an intelligence platform for accounting, focused on automation and communication, with AI as the doer and humans as the reviewers. It connects structured financial data with unstructured documents and conversations, giving AI the context to make accounting decisions, carry out the work, and support client communication.

Accounting professionals review results and handle exceptions, with clear visibility into the decisions behind the work. We build alongside our own accounting team, using real cases and reviewer feedback to develop evals and continuously improve reliability.

We're looking for product minded fullstack engineers to own features end to end at Sanna, with a strong focus on applied AI. You'll talk to users, understand their workflows, and help decide what to build. You'll integrate models, design AI workflows, and build the interfaces, APIs, and integrations around them. You'll ship to production, measure what works, and use those insights to improve both AI performance and the product.

• Own features end to end, from talking to users and shaping solutions to building, shipping, and improving them.

• Build AI workflows with models, tools, and relevant context. Develop evals grounded in real accounting cases to understand failure modes and make the workflows reliable.

• Own the results after launch. Measure user outcomes, accuracy, latency, and cost, and use those insights to improve the product.

• Strong fullstack experience and comfort building across interfaces, backend services, APIs, and data.

• Experience putting LLMs into production, with an understanding of context, tool use, evals, and the limits of model behaviour.

• Product instinct. You want to understand users' problems, make thoughtful tradeoffs, and measure whether your work helps.

• Strong engineering judgment. You can move quickly while giving correctness, security, and reliability the attention they need.

• A track record of taking ownership, communicating clearly, and following through from an ambiguous problem to a working solution.

Our engineers work across the whole stack, from product interfaces to AI workflows and the systems that power them. Some of the tools we build with include:

• Frontend: React

• AI: Mastra, AI gateway

• Workflows: Inngest

• Data & Backend: Supabase

• Cloud: Vercel

We're always exploring tools that help us build better products and move faster.

• We care: We care about the work we deliver. We care about and respect our teammates, and we bring out the best in them. We care about our clients and what they actually need.

• We challenge: We're here to change the way the world works. We set sky-high ambitions, question the status quo, and test what was thought impossible. We don't accept stated truths – we try, we learn, we redo.

• We move fast: We're doing what no one thought possible. We build fit-for-purpose and parallelize when we can. We do what needs to be done, every day – and when competitors copy us, they're already six months behind.