Executive/ Leadership/ ManagementTechnical/ IT Related

• Legal name and if you have a preferred or nickname:
• Linked In:
• Best contact info (Email, cell):
• Citizenship (US, Legal/Permanent Resident Green Card, or other):
• Availability:
• Where you live: (City, St, Zip)
• Willing to work 100% onsite, hybrid or remote:
• Willing to relocate if necessary:
• City, State, Zip and desired geographical work locations:
• Active passport and willing to travel if necessary
• Hourly/salary history and expectations:
• Sizes of Staff overseen:
• Budgetary Responsibility:
• Hierarchy/Report to, Our client has a SaaS platform that automates accounts-payable workflows, payment processing, and financial operations for hedge funds, private equity firms, fund administrators and family offices. The platform handles invoice capture, approval routing, vendor management, multi-entity accounting, and payment execution.

They are entering a new phase of product development: embedding AI and agentic capabilities directly into their platform to transform how financial operations teams work. This is the most important technical initiative for our client, and this role will lead it., 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.

You will define how AI is integrated into the SaaS platform: which workflows become agentic, how models interact with our domain data, how we build trust and safety into autonomous financial operations, and how we evolve the platform architecture to support these capabilities at scale.

This is a high-autonomy, high-impact role. You will work across the full stack-from prompt engineering and model orchestration to API design, data pipelines, and frontend integration-and collaborate closely with product, design, and domain experts to ship features that meaningfully change how our clients operate.

Tech Stack & Environment

You will work across the following stack. Deep expertise in every layer is not required-but you should be comfortable navigating a polyglot codebase and making architectural decisions that span these technologies.

• Cloud - Microsoft Azure (App Services, Functions, Storage, Service Bus, Key Vault)
• Backend - C# / .NET and Python (dual-language codebase)
• Frontend - Angular / TypeScript
• Database - SQL Server
• Architecture - Containerized microservices (Docker, Azure Container Apps / AKS) and Azure App Services
• DevOps - Azure DevOps (CI/CD pipelines, repos, boards)
• AI Tooling - Claude (Anthropic) and Cursor for agentic development workflows
• Integrations - MCP servers, REST APIs, file-based feeds (NACHA, ISO 20022, SWIFT), OCR/email ingestion, Agentic Architecture & System Design
• 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.

AI Feature Development

• 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.

Technical Leadership

• 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.

Cross-Functional Collaboration

• 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., The specifics will depend on where you see the highest leverage, but examples of the kind of work we envision:
• Agentic AP assistant - an AI agent that can process incoming invoices, match them to POs, route for approval, flag anomalies, and draft payment instructions with human confirmation.
• Natural-language financial queries - a conversational interface that lets controllers ask questions about payables, cash positions, and vendor history without building reports.
• MCP integration layer - a set of MCP servers that expose core capabilities to external AI tools, enabling clients to interact with the company’s Claude, Copilot, or their own agentic systems.
• Intelligent onboarding - AI-powered data extraction and mapping that accelerates client onboarding from weeks to days.
• Evaluation and monitoring infrastructure - automated testing, quality scoring, and production observability for every AI-driven feature.

How We Measure Success

1. Shipped AI features that clients actively use and that measurably reduce manual work in financial operations workflows.
2. Reliable agentic systems - autonomous workflows that operate safely within defined guardrails, with low error rates and clear audit trails.
3. Engineering velocity - the team ships AI features faster over time because of the infrastructure, patterns, and tooling you establish.
4. Technical credibility - you are the person engineering, product, and leadership turn to for AI/agentic technical decisions, and your judgment is consistently sound.
5. Team capability growth - engineers across the team are more effective at building AI-powered features because of your mentorship and the standards you set.

Why This Role Matters

• 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.

• You will work across the below following stack. Deep expertise in every layer is not required-but you should be comfortable navigating a polyglot codebase and making architectural decisions that span these technologies.

• 8+ years of professional software engineering experience, with significant time spent building production systems at scale.
• 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., * Experience building MCP servers or integrations, or deep familiarity with the Model Context Protocol ecosystem.
• Domain experience in FinTech, payments, accounting automation, fund administration, or financial operations.
• Experience with AI-assisted development tools (Claude Code, Cursor, Copilot) and a philosophy for how they change engineering workflows.
• Background in building trust and safety systems for AI: content filtering, output validation, human-in-the-loop patterns, and audit logging for autonomous actions.
• Experience with Azure cloud services, SQL Server, or Azure DevOps.
• Familiarity with financial data formats and integrations: NACHA, ISO 20022, SWIFT, or accounting system APIs (QuickBooks, NetSuite, Sage).
• Prior experience at a Staff/Principal level or as a founding/early engineer at a startup where you shaped technical direction., * How many years of experience and how recent is your experience in a SaaS financial environment:
• How many years of experience and how recent is your experience in a Product Engineering role taking large language models, tool-use patterns, and agentic frameworks and ship them as reliable, production-grade features that financial operations teams depend on daily:
• How many years of professional software engineering experience, with significant time spent building production systems at scale, and most recent year:
• How many years of hands-on experience building AI/ML-powered product features-not research prototypes, but shipped, production software that real users depend on, and most recent year:
• How many years of deep experience do you have with LLM integration: prompt engineering, function/tool calling, RAG architectures, agent orchestration, and evaluation frameworks, and most recent year:
• How many years of experience do you have with software engineering fundamentals: system design, API design, data modeling, distributed systems, and production operations, and most recent year:
• How many years of experience do you have 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, and most recent year:
• How many years of experience do you have with Python and/or TypeScript. Familiarity with SQL and relational databases, and most recent year:
• How many years of experience do you have leading technical initiatives that span multiple teams or systems, with strong written communication (RFCs, design docs, ADRs) , and most recent year:
• How many years of experience do you have with Demonstrated ability to work with ambiguity-translating broad product goals into concrete technical plans and shipping iteratively, and most recent year:
• How many years of experience do you have building MCP servers or integrations, or deep familiarity with the Model Context Protocol ecosystem, and most recent year:
• How many years of experience do you have with Domain experience in FinTech, payments, accounting automation, fund administration, or financial operations, and most recent year:
• How many years of experience do you have with AI-assisted development tools (Claude Code, Cursor, Copilot) and a philosophy for how they change engineering workflows, and most recent year:
• How many years of experience do you have with building trust and safety systems for AI: content filtering, output validation, human-in-the-loop patterns, and audit logging for autonomous actions
• How many years of experience do you have with Azure cloud services, SQL Server, or Azure DevOps, and most recent year:
• How many years of experience do you have with financial data formats and integrations: NACHA, ISO 20022, SWIFT, or accounting system APIs (QuickBooks, NetSuite, Sage), and most recent year:
• How many years of experience do you have at a Staff/Principal level or as a founding/early engineer at a startup where you shaped technical direction, and most recent year, * 8+ years of professional software engineering experience, with significant time spent building production systems at scale.
• 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.

Financial operations is one of the highest-value domains for AI-it is structured, repetitive, high-stakes, and ripe for intelligent automation. But building AI for finance requires more than model access. It requires deep product thinking, rigorous engineering, and a respect for the fact that these systems move real money.

This role is the technical cornerstone of the company’s AI strategy. You will not be bolting AI onto an existing product. You will be fundamentally reshaping how the product works-and how our clients work-by bringing agentic intelligence into every layer of financial operations.

If you want to build AI systems that matter, at a company where you can see the direct impact of your work on real businesses, this is the role.