Product Engineer, Agents

About Callimacus

At Callimacus, we’re working to change how people interact on the web. For the past 30 years, the user experience as we know it has been anchored to a typographic paradigm — predefined navigation trees of pages, sections, and menus — established in the Nineties when the web was born.

As the way people get informed, entertained, and shop evolves, traditional websites and interfaces are losing relevance, and the tools available limit the creative evolution of digital experiences. Callimacus was born from the conviction that the whole web experience can and should be reinvented.

So we built the engine for a different kind of digital experience. Callimacus is a multi-agentic platform that plugs into a company’s existing stack and reads multi-dimensional signals to understand what a visitor wants in the moment. Then, in milliseconds, our proprietary technology composes the entire interface around that intent, selecting the most relevant content and components as the person interacts.

Callimacus was founded in 2024 with the early backing of Brunello Cucinelli — one of our first investors, and now one of our customers. We launched in January 2026 to strong organic interest from enterprise customers, and recently raised from Salesforce Ventures the largest AI investment they have made in Italy, and one of their most significant in Europe.

We are a small, product-focused, founder-led team. We work on hard problems that haven’t been solved before — by us or anyone else — and the people who join now get to solve them. We move fast, with high agency and strong ownership.

You’ll join a small senior team at the point where the platform’s foundations are still being set. Callimacus is in production with demanding customers, and the architecture, the performance envelope, and the shape of the developer experience are all still yours to influence. Decisions you make in your first months will still be load-bearing in three years.

• Own the orchestration layer. Design how our agents turn multi-dimensional visitor signals into intent, and intent into a fully composed interface — in milliseconds, in production, for demanding enterprise customers.
• Put inference on the critical path — and keep it fast. Model routing, caching, fallbacks, and latency budgets for a system where “the model is thinking” is not an acceptable state.
• Build the retrieval and selection pipeline. Embeddings, vector search, ranking, and the content-selection logic that decides what a visitor sees next.
• Make agent behavior measurable. Evals, tracing, and feedback loops, so quality is an engineering discipline rather than a feeling.
• Shape how customers extend the system. Tools, guardrails, and configuration — the primitives others will build on.

These are the same for every role at Callimacus. We hire people who get the job done and care about the end result — the product, the experience, the people using it.

• Ownership. You feel deeply responsible for your work and behave accordingly — from design through production and after. You don’t wait to be told what to do; you see problems and act. “It’s not my job” is not part of your mindset.
• Invention. You light up at hard problems and are creative at finding solutions. You experiment, get your hands dirty, and land things. You hold very high standards and always look for ways to improve.
• Team-oriented. You’re someone others can count on. You support the best idea even when it’s not yours, disagree productively, give and take feedback, share credit, and take on unglamorous work when that’s what the team needs.

The craft bar for this role: Strong TypeScript and Node.js, with a track record of shipping production systems. AI systems literacy: RAG, embeddings, vector databases, and agent orchestration are part of your working vocabulary. You don’t need to have trained a model; you do need to know what breaks when inference sits on the critical path.

We’re early, and nobody is strong in all of these — we don’t expect you to be. Depth in two or three, plus curiosity about the rest, is what wins. If that’s you, apply even if you don’t tick every box.

• Agent orchestration and multi-step LLM workflows
• RAG, embeddings, and vector databases in production
• Prompt and eval engineering at scale
• Streaming and real-time systems
• Backend performance work — latency budgets, caching, load
• Data pipelines feeding AI systems

• Experience as an early engineer at a startup or fast-growing company
• Shipped inference-heavy or data-intensive products
• Open-source work in the AI tooling space