Staff Engineer (AI)

Location: Onsite in Munich, Germany, or Madrid, Spain

Company

hirify.global builds autonomous agents for finance operations, covering accounts payable and accounts receivable workflows.

What you will do

• Design the multi-agent architecture, including agent boundaries, event contracts, orchestration, authorization, and the separation of LLM reasoning from deterministic enforcement.
• Build agentic workflows for dispute resolution, dynamic discounting, invoice matching, reconciliation, anomaly detection, and payment execution.
• Develop an integration framework for ERPs, banking APIs, accounting platforms, Gmail, Drive, and Slack, including authentication, credential lifecycle, and data normalization.
• Own platform primitives including an append-only PostgreSQL event store, hash-chained audit logs, cryptographic event verification, policy-based workflow constraints, row-level multi-tenancy, tenant-scoped credentials, Cerbos authorization, and MCP security.
• Design zero-trust controls, source-data verification, outbound-content review, prompt-injection defenses, and support European e-invoicing requirements including EN 16931.
• Set the engineering standard through architecture decision records, design reviews, on-call practices, and direct observation of finance-controller and accounts-payable workflows.

Requirements

• 8+ years shipping production systems, currently operating as a Staff, Principal, Lead individual contributor, or founding engineer, with experience carrying architecture through a scaling step.
• Strong systems-design skills covering agent boundaries, failure modes, trust boundaries, contract evolution, and non-retry-safe money movement.
• Production depth in Python and/or TypeScript and deep PostgreSQL experience, including event sourcing, row-level security, indexing tradeoffs, and schema evolution under load.
• Hands-on experience with LLM-powered systems, agent orchestration frameworks such as LangGraph or LangChain, and document AI tools such as LlamaIndex or LlamaParse.
• Ability to choose and defend when to use LLMs, rules engines, or traditional machine learning.
• Production experience designing data pipelines, integration architectures, or event-driven systems.
• Security awareness covering untrusted input, pipeline security, and segregation of duties.
• Technical leadership through teaching code reviews, adopted designs, and improving other engineers’ effectiveness, plus effective use and review of AI coding tools for LLM integration and authorization code.
• Deep domain knowledge in at least one of accounts payable, accounts receivable, or procurement, with working fluency across the remaining purchase-to-pay and order-to-cash processes.
• Fluency with ERPs such as NetSuite or Dynamics, SMB finance stacks, the sub-ledger/general-ledger relationship, and period-close constraints on agent actions.

Nice to have

• Production experience with Peppol and EN 16931 or bank connectivity via ISO 20022.
• Production experience with digital signatures, cryptographic primitives, hash chaining, or tamper-evident logs.
• Experience with SOC 2, GDPR, or data-residency engineering in a regulated environment.
• Founded a company or worked as employee 1–5 in a startup.

Culture & Benefits

• Individual-contributor role at the top of the engineering ladder with no direct reports and full technical authority over the shared architecture.
• Onsite work based in Munich or Madrid.
• Strong emphasis on architecture documentation, engineering review standards, operational ownership, and deliberate product scope.