Finance AI Engineer ( Manager )

Overview

In this role you will build and operate production-grade AI applications for finance processes, turning experimentation into scalable capabilities. You’ll work close to CFO-facing priorities, translating finance requirements into observable, secure software delivered within delivery pods. Expect to shape agent-based workflows, AI evaluation, and user interfaces that enable finance teams to review and govern AI actions. You will balance cutting-edge technology with enterprise risk, security, and operational reliability to impact cash, profitability and growth.

Responsibilities

• Design, build and deploy agentic workflows in live finance processes (reconciliations, journals, disputes, collections, variance explanation) with clear acceptance criteria and controlled failure handling.
• Implement LLM application patterns (tool calls, structured outputs, retrieval, multi-agent orchestration, versioned prompts).
• Integrate with ERP/EPM systems and document repositories via secure APIs, data extraction, transformation, and error handling.
• Write evaluations, instrument agent behavior, ensure observability, and validate quality, latency and cost with automated tests and red-team scenarios.
• Create interfaces for finance users to review, approve, override and evidence agent actions, including provenance and accessible error recovery.
• Package and operate solutions using cloud AI services, containers/serverless, CI/CD, IaC, secrets management, monitoring and rollback.
• Collaborate with finance users, architects and data engineers to clarify requirements and document runbooks.
• Contribute reusable patterns and components to the practice asset base with implementation guidance.

Key requirements

• Strong software engineering: Python plus at least one other production language (e.g., TypeScript), version control, testing, CI, secure coding, SQL, API design.
• Hands-on LLM application development: tool usage, structured outputs, retrieval, embeddings, vector/graph retrieval, prompt/config management, and enterprise data integration.
• Experience with evaluation, observability and LLMOps/AgentOps including versioning, monitoring, release/rollback and cost/latency analysis.
• Understanding of secure enterprise integration and sensitive-data handling (authentication, authorization, secrets, logging, PII-aware design).
• Ability to collaborate with non-technical finance users to translate needs into testable requirements and explain options and risks.
• Minimum of 6 years of relevant professional experience.

• Cross-functional collaboration
• Clear communication of risks and trade-offs
• User-focused problem solving
• Python and a secondary production language (e.g., TypeScript)
• LLM tooling: tool use, structured outputs, retrieval, agent frameworks
• Embeddings, vector or graph retrieval

…