RYAN ZERNACH

Senior AI Systems Engineer

Ryan_Zernach_2025_Senior_AI_Systems_Engineer_Remote_United_States

BUILDING RELIABLE

HEALTHCARE AI

SCALING PRODUCTION

LLM SYSTEMS

ENGINEERING TRUSTED

AI INFRASTRUCTURE

DELIVERING INTELLIGENT

PATIENT IMPACT

⚡️ ZurboTax: AI Engineering for Federal Tax Preparation

I did not use AI as a gimmick for tax season. I built a private tax-engineering system that ingests fragmented financial records, normalizes them into deterministic artifacts, computes tax workpapers, autofills official forms, and assembles a review-ready submission packet with field-level audit payloads. After 12 years of operating LLCs, this became my fastest, cleanest, and most professional preparation cycle because the process finally behaved like software engineering, not seasonal spreadsheet triage.

Related Links
Finequities: SOC 2 Compliant Mobile App
Agentic federal tax preparation workflow image showing Codex, GitHub, AI, LLMs, and automations

Why This Is Memorable

Most AI tax stories are prompt experiments. This one is production discipline: strict validation gates, year-scoped filing directories, deterministic JSON and markdown artifacts, official form autofill, and a merged packet build that fails loudly when requirements are incomplete.

Why This Is Important

This project demonstrates startup-critical execution behavior: fast shipping with hard guardrails, transparent automation, deterministic outputs, and systems that can survive scrutiny from investors, operators, and customers.

What Makes It Different

I engineered an end-to-end pipeline where every critical output can be rerun, inspected, and defended. That is the bar I set for AI systems that touch public trust workflows.

Technical Deep Dive: tax-filings

The production spine behind this project lives in my `tax-filings` repo, not in marketing copy. I structured it as a year-aware filing system with deterministic outputs, explicit validation, and inspectable form payloads so every important step can be reviewed, rerun, and defended.

Repository architecture and execution flow

Input normalization and correctness controls

Official form autofill and auditability

Submission packet generation and safety boundaries

Reliability mindset for high-consequence systems

Failure modes I engineered against

Summary

Most people treat taxes like an annual emergency. I treated them like a systems problem. The objective was to replace panic cleanup with a repeatable engineering workflow that preserves quality under deadline pressure.

Execution Surface

A transaction-ingestion and classification engine feeding a year-scoped filing pipeline: validated raw inputs, normalized outputs, computed workpapers, autofilled official forms, and a merged filing packet.

Outcome

The biggest win was operational credibility. Preparation became faster and cleaner because the process became inspectable, deterministic, and reusable instead of ad hoc.

Key Details

The sections below cover the original tax-prep pain, the finance system itself, and why GitHub plus Codex changed the quality of the workflow.

Why I built this in the first place

What the dashboard actually automated

How GitHub and Codex fit into the loop

What changed by tax season

What Moved Toward Autopilot

  • Multi-source transaction ingestion and normalization into one review surface.
  • Business-versus-personal classification persistence through manual overrides and reusable rules.
  • Tax-year-specific workpaper generation with reproducible JSON, markdown, and PDF artifacts.
  • Official form autofill with adjacent field payload audit logs.
  • Submission checklist and packet assembly that enforces required-form presence.

LLM Infrastructure Alignment

The engineering posture here mirrors what elite AI product teams need: deterministic pipelines, strict validation, transparent assumptions, and explicit human accountability on final decisions.

Principles I Enforced

  • Deterministic outputs over vibe-driven spreadsheets.
  • Human accountability over unchecked autonomy.
  • Auditability over black-box convenience.
  • Repeatable runbooks over heroics.
  • Measured operational discipline over one-time demo theater.

Senior AI Systems Engineer

This is the operating style I bring as a Senior AI Systems Engineer: move fast without becoming reckless, automate aggressively without creating opaque risk, and ship systems that stay legible when stakes rise.

  • I can design AI systems that operate under scrutiny, not just in demo environments.
  • I can translate ambiguous operational workflows into deterministic pipelines with explicit controls.
  • I can ship automation that accelerates throughput without surrendering accountability.
  • I can build systems whose outputs are inspectable, reproducible, and defensible in front of reviewers.