AI Engineer ( Manager )

Overview

In this role you engineer production-grade AI solutions for finance processes, sitting in a delivery pod and translating finance requirements into secure, observable software. You will build agent-based workflows, integrate with ERP/EPM systems, and operate AI services that influence cash, profitability, risk and growth. You’ll work closely with finance users and engineers to deliver reusable patterns and runbooks, shaping enterprise-wide AI capabilities with measurable business impact.

Responsibilities

• Build and deploy agentic workflows in live finance processes (reconciliations, journals, disputes, collections, variance explanation) with clear acceptance criteria and controlled failure behavior
• Implement LLM application patterns (tool use, structured outputs, retrieval, multi-agent orchestration, prompt/config management)
• Integrate with ERP/EPM systems, document repositories and workflow tools using secure APIs, data extraction, transformation and error handling
• Write evaluations, instrument behavior, ensure visibility of failure modes with automated tests, observability, latency and cost measures
• Create interfaces for finance users to review, approve, override and evidence agent actions with provenance and accessible error-recovery
• Package and operate solutions using cloud AI services, containers/serverless, CI/CD, infrastructure as code, secrets management, monitoring and release controls
• Collaborate with finance users, architects and data engineers to clarify requirements and document runbooks
• Contribute reusable patterns and components to the practice asset base (code, evaluation assets, reference implementations)

Key requirements

• Strong software engineering discipline (Python and at least one other production language such as TypeScript), version control, testing, CI, secure coding practices
• Hands-on LLM application development (tool use, structured outputs, retrieval, agent frameworks, embeddings, graph/vector retrieval)
• Experience with evaluation, observability and LLMOps/AgentOps (versioning, monitoring, release, rollback)
• Understanding of secure enterprise integration and sensitive-data handling (authentication, authorization, secrets, logging, PII-aware design)
• Ability to work with non-technical finance users to translate needs into testable requirements while communicating risks and trade-offs
• At least 6 years’ relevant professional experience
• Desirable: front-end capability (React/Next.js) and exposure to SAP, Oracle, Workday, Anaplan or OneStream; experience with MCP, semantic retrieval, data engineering, event-driven integration; cloud deployment (Azure/AWS/GCP) with DataBricks, Snowflake, Palantir; containers/Kubernetes/serverless; delivery in regulated environments

• Collaborative communication
• Ability to translate business needs into technical requirements
• Constructive challenge and requirement refinement
• Python
• TypeScript or equivalent
• SQL

…