Staff Engineer, AI & Agentic Development

About the role

We are hiring a Staff Engineer to own the architecture, design, and delivery of AI-powered and agentic features. This is not an ML research role—it is a product engineering role for someone who can take large language models, tool-use patterns, and agentic frameworks and ship them as reliable, production-grade features that financial operations teams depend on daily.

Responsibilities

• Design and build the core agentic infrastructure: agent orchestration, tool-use frameworks, memory/context management, and guardrails for autonomous financial workflows.
• Define the architecture for how LLMs interact with the domain model—invoices, approvals, vendor records, payment instructions, accounting entries—safely and reliably.
• Build and maintain MCP (Model Context Protocol) servers and integrations that expose capabilities as tools for AI agents and external AI platforms.
• Design patterns for human-in-the-loop oversight, approval gates, and escalation paths in agentic financial workflows.
• Lead development of AI-powered product features: intelligent invoice processing, automated approval routing, anomaly detection, natural-language querying of financial data, and predictive cash-flow analysis.
• Build and iterate on prompt chains, retrieval-augmented generation (RAG) pipelines, and multi-step agent workflows tailored to financial operations.
• Implement evaluation frameworks: automated testing for AI outputs, regression detection, quality scoring, and production monitoring for model-driven features.
• Own the integration layer between LLM providers (Anthropic, OpenAI, etc.) and backend—model selection, fallback strategies, cost optimization, and latency management.
• Set technical direction for AI/agentic development across the engineering team. Write RFCs, architectural decision records, and technical specifications.
• Mentor engineers on AI integration patterns, prompt engineering, evaluation methodology, and safe deployment of model-driven features.
• Establish engineering standards for AI features: testing practices, monitoring, incident response, and responsible AI guidelines specific to financial data.
• Drive build-vs-buy decisions for AI tooling, frameworks, and infrastructure. Evaluate emerging tools and frameworks and make pragmatic adoption recommendations.
• Partner with product management to identify high-value AI use cases, scope MVPs, and define success criteria grounded in client outcomes.
• Work with the implementation team to understand client workflows and pain points that AI can address.
• Collaborate with security and compliance to ensure AI features meet regulatory requirements for financial data handling, auditability, and data privacy.

Qualifications

• 3+ years of hands-on experience building AI/ML-powered product features—not research prototypes, but shipped, production software that real users depend on.
• Deep experience with LLM integration: prompt engineering, function/tool calling, RAG architectures, agent orchestration, and evaluation frameworks.
• Strong software engineering fundamentals: system design, API design, data modeling, distributed systems, and production operations.
• Experience with at least one modern AI/agent framework (LangChain, LlamaIndex, Anthropic tool use, OpenAI Assistants, CrewAI, or similar) and a clear-eyed view of their trade-offs.
• Proficiency in Python and/or TypeScript. Familiarity with SQL and relational databases.
• Track record of leading technical initiatives that span multiple teams or systems, with strong written communication (RFCs, design docs, ADRs).
• Demonstrated ability to work with ambiguity—translating broad product goals into concrete technical plans and shipping iteratively.