AI Engineer - Document Intelligence & Financial Data Pipelines

• Own the AI extraction layer. Design and maintain high-accuracy pipelines that parse tabular, structured, and unstructured financial data from scanned and digital PDFs - trust statements, payroll documents, vendor reports - using Azure Document Intelligence and frontier LLM vision APIs.
• Build and harden PII redaction. Extend our in-house PDF redaction toolkit so that SSNs, EINs, account numbers, and names are masked programmatically before data crosses any external API boundary.
• Design reconciliation workflows. Implement the cross-referencing and matching logic - deterministic where Python or SQL wins, agentic only where justified - that reconciles data extracted from disparate financial sources.
• Deliver clean, documented REST APIs. Wrap AI workflows into secure FastAPI services with strict Pydantic-validated inputs and outputs that our core development team consumes with confidence.
• Enforce guardrails and run evals. Detect and reject low-confidence extractions, build automated regression suites against real documents, and maintain measurable accuracy benchmarks over time.
• Operate reliably on Azure. Deploy and monitor microservices on AKS, instrument with OpenTelemetry traces and metrics to Azure Monitor, and keep services auditable and production-grade.

• Python expertise. Deep proficiency with async Python, type annotations, and data manipulation; comfortable in a modern Python 3.12+ fully-typed codebase.
• LLMs and multimodal vision. Hands-on production experience with frontier LLM APIs (OpenAI, Anthropic, or equivalent) using vision capabilities to read complex multi-page financial tables.
• Structured AI outputs. Advanced use of Pydantic, Instructor, or native structured-output APIs to force LLMs into validated, system-ready JSON - not hoping the model behaves, enforcing it.
• Document intelligence and OCR. Proven experience with enterprise document parsing pipelines; prior Azure Document Intelligence or Azure Content Understanding exposure strongly preferred.
• Relational data discipline. Solid PostgreSQL data modeling and migration practices (SQLAlchemy/Alembic or equivalent); reconciliation logic lives in the database as much as in the pipeline.
• Security and data-handling mindset. Familiarity with financial data obligations, zero-data-retention LLM agreements, regional endpoints, and why redaction must precede the API boundary.

Nice to have

• Domain experience in accounting, fintech, legal, or audit-compliance contexts
• PDF internals: manipulating documents at the object or glyph level (pikepdf, pdfminer.six, pypdfium2, or similar)
• Orchestration with distributed task queues - our pipelines run as taskiq workers over RabbitMQ and Redis
• PII pipeline experience with privacy frameworks or custom NLP/regex hybrid engines
• Observability instrumentation with OpenTelemetry shipped to Azure Monitor

Pulled from the full job description

• Health insurance
• 401(k) matching
• Paid time off
• Vision insurance
• Dental insurance
• 401(k) 8% Match, * Annual salary range between $145,000 and $200,000 depending on experience
• Six weeks of paid time off
• Robust 401k plan with an 8% company match
• Comprehensive healthcare, dental, and vision insurance coverage
• Remote work tools and stipend program

Location & schedule

• Full-time employment
• Fully remote position open to candidates based in the United States

We are an established financial technology and services automation platform dedicated to bringing security, modern engineering, and high-accuracy AI workflows to complex compliance and accounting operations.

To apply, submit your resume and a brief note on a document extraction or AI pipeline project you’ve shipped - what the accuracy challenge was and how you measured success. We review every application and aim to respond within five business days.