AI Agents Solutions Architect - Finance

Favia's Global Finance team is the operational backbone of one of the world's most trusted and longest-standing crypto exchanges. The team spans accounting, FP&A, treasury, tax, and finance operations across multiple regulated entities and 70+ countries, managing the financial infrastructure that underpins everything from daily close to regulatory reporting to crypto-native asset reconciliation.

As financial complexity grows with Favia's global footprint, this role architectures and provides hands‑on building to scale growth. Finance operations at a globally regulated crypto exchange managing close cycles, reconciliations, reporting, treasury monitoring, and controls validation all generate substantial manual effort tied to critical financial and regulatory obligations. Errors carry audit, SOX, security ,and regulatory consequences.

You will serve as the primary architect and builder of the AI‑native finance operating system s role spans two simultaneous horizons: deploying production automation now and redesigning the finance architecture for the long term. Responsibilities span five core areas:

• Evaluate how financial work currently flows across the organization, including close, reconciliations, treasury, reporting, controls validation, and audit preparation.

• Identify capability gaps, manual bottlenecks, and integration failure points across systems including Net Suite, Black Line, Kyriba, Fireblocks, and Lukka.

• Benchmark current operations against best-in-class practices and emerging AI capabilities to build the Finance automation roadmap, prioritized by operational leverage and regulatory risk.

• Work directly with accounting, FP&A, treasury, and finance operations teams to translate process pain points into buildable automation requirements.

• Design the long-term architecture for an AI‑native finance operating system. Define how agentic systems interact with financial infrastructure, data pipelines, and control and reporting frameworks.

• Evaluate Favia's existing finance systems stack from first principles, including platforms and the interfaces and data flows between them. Identify opportunities to simplify the stack, reduce manual intervention, and define a scalable target architecture.

• Build an agentic finance layer that runs alongside the existing stack today, automating workflows while defining the migration path toward a more scalable, AI‑native architecture over time.

• Deploy production‑grade agentic workflows that automate finance operations: reconciliations, close processes, audit and reporting preparation, treasury monitoring, financial analytics, and controls validation.

• Build using modern AI tooling including Claude and Anthropic APIs, Python‑based orchestration, n8n or equivalent workflow engines, and MCP or similar agent coordination layers.

• Integrate internal and external systems by connecting APIs, data sources, and tools into unified automated workflows that deliver real operational leverage.

• Maintain human oversight where appropriate. Design for auditability and control integrity, not just efficiency.

• Establish guardrails that allow automation and agent behavior to operate safely in a SOX‑regulated financial environment. Define which controls are maintained, which are redesigned, and how workflow scope preserves control integrity.

• Build frameworks covering data classification, auditability, human‑in‑the‑loop checkpoints, failure detection, rollback mechanisms, regulatory compliance, and audit‑ready design documentation.

• Classify all automation builds by risk tier before work begins. No build goes to production…