AI Engineer

Description

Professional tax preparation begins with a messy set of documents and ends with a return that must be accurate. The company is building the modern tax engine and application that makes that process faster, more reliable, and easier for tax professionals.

We are looking for an AI engineer to own the intelligence layer across that workflow. You will design and maintain systems that turn documents into usable tax data, help tax professionals identify missing or inconsistent information, and review completed returns before filing.

This is not a role focused on a generic chat experiences. You will build production AI systems that operate on real financial documents and work alongside a deterministic tax engine, where accuracy, traceability, and thoughtful human control matter.

The Team

The company was founded by Angelo Policicchio, a CPA, and Akash Sadashivapeth, who met at Harvard Business School. Our engineering team brings decades of combined experience building deterministic engines for the financial services industry, where accuracy is non-negotiable. We’re building the company because nearly every tax return prepared by a CPA in America runs through one of a handful of tax engines built in the 1990s, and we’re building the first modern, API-first, IRS-approved engine to replace them.

What You’ll Work On

Document collection and classification: Build systems that collect client documents and identify what they are, including tax forms, financial statements, receipts, and supporting materials.

Extraction and normalization: Turn structured and unstructured documents into reliable, usable data. You will design workflows to extract fields, preserve source context, resolve ambiguity, and route low-confidence results for human-in-the-loop review.

Agentic return review: Build agents that examine a completed return alongside its source documents and relevant tax context. The system should identify missing information, inconsistencies, and potential errors, then explain findings clearly and propose corrections for a tax professional to review.

The AI experience: Shape how tax professionals understand, trust, and act on AI output. This includes confidence, citations to source documents, review workflows, correction flows, and clear boundaries between suggestions and final decisions.

Evaluation and reliability: Build the evaluation, observability, and feedback systems needed to measure extraction quality, agent performance, and user outcomes over time.

Requirements

• Experience building robust document OCR and extraction systems, including working with PDFs, forms, scanned documents, and financial data, and applying modern LLM-based methods for document understanding, parsing, and structured data extraction.
• Experience designing scalable evaluation frameworks that reliably benchmark quality, including defining evaluation datasets, ground-truth labels, scoring methodologies, and statistical analyses for structured and unstructured documents.
• Strong judgment about evaluating design, observability, reproducibility, and human-in-the-loop workflows.
• A bias toward shipping and learning from real-world document and model behavior, paired with a high bar for accuracy, auditability, reliability, and actionable measurement.
• What Success Looks Like
• In your first 30 days, you’ll understand and optimize the document and return-preparation workflow, ship meaningful improvements, expand extraction coverage, and pinpoint the most time-consuming manual steps where AI can improve accuracy, speed, or consistency.
• By 60 days, you’ll own a production workflow for document classification and extraction with clear quality metrics and a feedback loop from users.
• By 90 days, you’ll have established the foundation for expanding AI across the application into an AI-powered review experience that helps tax professionals catch issues earlier and prepare returns with greater confidence.

Conditions

We are a small team with high ownership and little separation between product and engineering. You’ll work directly with tax professionals, collaborate with engineers building the tax engine and application, and make consequential decisions about how AI becomes part of a new tax platform.

Skills: Python, Machine learning, LLMs, Fine-tuning, Evals, AI Agents

Experience: 3+ years

Visa: US citizen/visa only