Ancora is building an AI-native accounting software that replaces traditional accounting management systems. We're not improving the status quo - we're replacing it entirely: from software that waits for human input to an autonomous agent that performs accounting under professional supervision.
We're an Italian startup based in Milan. Our model combines a technology platform that automates the operational work these firms do every day: bookkeeping, tax filings, document management, compliance deadlines with a roll-up strategy — acquiring and consolidating accounting firms (studi commercialisti) across Italy.
The vision is clear: free accounting professionals from repetitive tasks so they can focus on what actually requires human judgment — strategic consulting, client relationships, and growing their practice. We're building the infrastructure that makes this possible at scale.
Where we are today. We're venture-backed by some of Italy's best investors, with our first studio acquisitions underway. The product is greenfield — zero legacy code, modern stack, built from scratch. Our engineering team is designing the entire architecture now. The decisions we make today will shape the system for years.
What makes Ancora different. We own the problem end-to-end: we build the technology, we acquire the firms, we operate the service. This means we control the feedback loop between what accountants need and what we build. We're not selling software to reluctant buyers — we're building it for firms we operate. The technology has to work because our business depends on it. Italian accounting is deeply regulated, complex, and largely untouched by modern software. The domain complexity is real, and that's what makes it interesting.
About the Role
As our first Backend Engineer, you'll architect and build the service layer that sits between our AI agents and the accounting domain. This is not a collection of CRUD APIs — it's the deterministic half of a hybrid AI architecture, designed to be consumed by autonomous agents using Model Context Protocol (MCP).
Your mandate: enforce business invariants. Whatever our AI agents propose, your services validate it against complex business rules. Invalid operations should be architecturally impossible.
The technical challenges. You'll design agent-first APIs that AI agents can reliably call without human intervention, with structured responses, clear error boundaries, and predictable composition. You'll model complex state machines — operations with irreversible transitions and cascading side effects — as APIs that are both correct and easy to reason about. Multi-tenant isolation at scale means guaranteeing data isolation across thousands of companies processed concurrently, preventing context leakage at every layer. You'll handle concurrency and idempotency: race conditions, duplicate events, and distributed operations with rock-solid guarantees. And you'll build observability for AI — capturing full decision context for every agent action to enable debugging and continuous improvement.
What You'll Do
Build the core service layer. Design and implement MCP-based APIs that AI agents can reliably consume. Model complex business operations as deterministic, composable services with validation logic that makes invalid states impossible. Build calculation engines that produce auditable results and state machines for irreversible transitions. Design PostgreSQL schemas optimized for agent workloads and handle long-term data evolution.
Own the distributed infrastructure. Build event-driven pipelines with idempotency guarantees and concurrency control. Implement multi-tenant isolation at every layer: row-level security, credential-based access control, architectural safeguards against context leakage. Integrate message brokers for asynchronous processing with exactly-once semantics. Scale isolation guarantees to thousands of concurrent tenants.
Ensure observability and continuous improvement. Instrument services to capture full decision context for every agent action. Design correction workflows that preserve audit trails and enable human oversight. Implement anomaly detection to surface unusual patterns for review. Build feedback loops that improve agent performance over time.
What We're Looking For
Must Have
* 3+ years of backend engineering experience in production environments.
* Strong proficiency in Python, Go, Java, or similar statically-typed languages.
* Deep experience with PostgreSQL — transactions, constraints, indexing, query optimization.
* Hands-on experience building REST APIs or gRPC services with proper validation and error handling.
* Understanding of event-driven architectures — message brokers (Kafka, RabbitMQ, or similar), idempotency, eventual consistency.
* Experience with testing — unit tests, integration tests, contract tests for APIs.
* Ability to read and implement from technical specifications and domain documentation.
* Strong sense of code quality — maintainable, testable, well-documented code.
Nice to Have
* Cloud environments (AWS preferred) and infrastructure as code (Terraform).
* Model Context Protocol (MCP) or similar agent-to-service communication protocols.
* APIs designed for AI agent consumption — structured responses, clear error semantics, tool-use patterns.
* Fintech, accounting, or financial services — double-entry bookkeeping, reconciliation, audit trails.
* Multi-tenant architectures — row-level security, tenant-aware middleware, credential scoping.
* Domain-driven design (DDD) — bounded contexts, aggregates, domain events.
* Event sourcing patterns.
* Italian accounting or fiscal regulations — helpful but not required.
* Observability tools — structured logging, tracing, metrics (Prometheus, Grafana, or similar)..
Mindset
* Pragmatic perfectionist. You care deeply about correctness but know when to ship and iterate.
* Domain-curious. You want to understand why the rules exist, not just implement them mechanically.
* System thinker. You see how services compose into a larger architecture and design for that context.
* Collaborative. You work closely with AI engineers, domain experts, and future team members as the team scales.
Why This Role is Interesting
* First engineer. You'll architect the entire service layer from scratch and set the technical direction for the backend stack — the decisions you make now will shape the system for years to come.
* Agent-first API design. You'll build services consumed by AI agents using MCP, not traditional web UIs — a fundamentally different design challenge.
* Deep domain complexity. Accounting is not CRUD. You'll model intricate business rules, temporal constraints, and multi-dimensional state machines.
* Hybrid AI architecture. You'll build the deterministic layer that makes autonomous AI agents trustworthy in a regulated domain.
* High ownership. You'll own the full stack from API design to database schema to production deployment.
* Greenfield with modern practices. Zero legacy code, CI/CD from day 1, daily production deploys — build the right way from the start.
* Growth environment. As the team scales, you'll have opportunities to grow your impact and potentially take on leadership responsibilities.
* Real-world impact. Your services will process the accounting for thousands of Italian SMEs, directly affecting their compliance and financial operations.
What We Offer
* Office First. Collaboration is easier and more effective in person in our Milan HQ. You can also enjoy working from home up to 30% of the time, while enjoying great company during our three core days in the office.
* Compensation. €50,000 – €75,000 gross annual salary, based on experience.
* Equity. Meaningful stock options package, based on experience and scope. Equity is offered with 0 strike price and a strong upside potential given stage of the company
* Benefits. Meal vouchers and fringe benefits (1k x year).
* Team. Direct reporting to the CTO; work closely with the founding team.
* Autonomy. Strong voice in technical decisions and architecture choices, collaborative approach to building the right solutions.
* Growth. As the team scales, opportunities for increased scope and impact.
How to Apply
Send your CV to talent@ancora.work with a brief note on why this role interests you.
We're an equal opportunity employer. We value diversity and encourage applications from people of all backgrounds.