ResumeGeni

ResumeGeni is an AI-powered resume builder that optimizes documents for the specific applicant tracking system the target employer is running — Workday, Greenhouse, Taleo, iCIMS, Lever, and the dozens of others enterprise hiring depends on. The studio operates it as a wholly-owned product (legal name: 941 Apps, LLC dba ResumeGeni) and it is the studio's flagship.

What ResumeGeni does for job seekers

• Per-ATS optimization. Tailors resume structure, section ordering, and keyword density to the parsing engine of the target ATS instead of treating "ATS-friendly" as a single standard.
• Job-description tailoring. Parses the actual posting, extracts required skills and qualifications, and rewrites the resume against the role's real language — not against a generic role template.
• 77-language translation. Full resume translation with locale-aware formatting for country-specific norms.
• Three export templates. Minimal, Executive, and Modern. Word and PDF formats designed to parse reliably across every major ATS.
• ATS-specific guides. A documentation library covering every major ATS, written from the inside.
• Job board. 1.1 million active job listings, aggregated and de-duplicated.

Why this product exists, and why the studio shipped it

Applicant tracking systems are the gatekeepers of modern hiring. Every major employer runs one. These systems receive resumes, parse them into structured data, and present that data to recruiters. The problem is that parsing is lossy. Tables, columns, headers, footers, images, and creative formatting routinely break the extraction process — qualified candidates get filtered out before a human ever looks at their application. Not because of their experience or skills, but because of how their resume was formatted.

Blake spent twelve years at ZipRecruiter, rising from design engineer to VP of Product Design. He designed interfaces used by more than 110 million job seekers. The thing that struck him most across that decade wasn't any individual feature — it was the gap between what candidates submitted and what recruiters actually saw. He saw it from both sides: the recruiter's frustration with garbled parsed profiles, and the candidate's silence after sending dozens of applications into systems that couldn't read them.

The full personal case study, including the ZipRecruiter background and the design principles that shaped the product, lives on blakecrosley.com/work/resumegeni. This page is the studio's product overview.

Why every ATS is different

One of the first things the studio learned building ResumeGeni was that "ATS-friendly" is not a single standard. Each platform has its own parsing engine with distinct behaviors.

Workday is the most widely deployed enterprise ATS. It handles standard formatting well but struggles with multi-column layouts and non-standard section headers. Its internal search uses keyword matching, not semantic understanding — the exact phrasing matters.

Greenhouse takes a different approach. Rather than scoring candidates algorithmically, it surfaces profiles to recruiters through structured search. Recruiters search by skills, titles, and qualifications — which means the parsed data needs to be clean enough to match those searches. Greenhouse's parsing is solid on standard documents but punishes creative formatting.

Taleo (now Oracle Recruiting Cloud) is the strictest parser the studio has encountered. It requires specific file formats, breaks on tables and columns more aggressively than any other system, and has rigid expectations about section order. Many government and large enterprise employers still run Taleo.

iCIMS has quirks of its own — particularly around how it handles iframe-based job listings and its approach to candidate data extraction. Widely used in healthcare, retail, and mid-market employers.

Lever is popular with startups and tech companies. Its opportunity-based model means recruiters see candidates in context, not just as parsed data. The parsing still needs to work for search and filtering.

The product's per-ATS rules come from documenting these differences exhaustively. Per-platform guides live in the ResumeGeni blog and explain the parsing quirks to job seekers directly.

How it was built

The AI layer uses Anthropic's Claude (Opus model) for content generation and analysis. The studio runs Opus exclusively for user-facing AI calls; cheaper models produce cheaper output, and the product competes on quality, not throughput. But the real value isn't the AI — it's the ATS domain knowledge baked into the system. Knowing that Taleo requires single-column layouts, that Workday needs exact keyword matches, that Greenhouse recruiters search specific fields — that knowledge is what turns generic resume advice into specific, testable optimization.

The tech stack reflects the studio's house bias: FastAPI on the backend, HTMX and Alpine.js on the frontend, Jinja2 templates, server-rendered HTML with progressive enhancement. No heavy JavaScript framework. No client-side routing. The same no-build pattern is on every product the studio ships, and the reasoning is the same every time: ship fast, measure everything, iterate on evidence.

Two design principles guided the product. Show the work. Most resume tools are black boxes — upload your resume, get a score, pay to see the fixes. ResumeGeni explains what it's doing and why. If Taleo will reject your two-column layout, you should know that before you apply. If a job description requires "Kubernetes" and your resume says "container orchestration," you should understand the keyword gap. Start with the data. The product is built on a corpus of real job listings and real ATS behaviors, not generic advice. The keyword recommendations come from analyzing actual job descriptions across industries. The formatting rules come from testing documents against actual ATS parsing engines.

What the studio learned

Building ResumeGeni confirmed something the studio suspected at ZipRecruiter: the gap between job seekers and hiring systems is largely a formatting and communication problem, not a qualification problem. The candidates exist. The jobs exist. The technology in between is what breaks the match.

The most impactful work wasn't the AI generation — it was the ATS research. Understanding exactly how each platform parses, searches, and presents candidate data. That knowledge is what makes the optimizer's recommendations specific instead of generic. If you're trying to navigate this yourself, the ATS comparison guide on ResumeGeni documents what the optimizer respects, in plain language, free.

Frequently asked

What does ResumeGeni do that other resume builders don't?

It optimizes a resume against the specific applicant tracking system the target employer is running. Most resume tools treat "ATS-friendly" as one standard; in reality every major ATS — Workday, Greenhouse, Taleo, iCIMS, Lever — parses resumes differently. ResumeGeni's per-ATS rules come from twelve years inside hiring technology, not from generic advice.

Who built ResumeGeni?

ResumeGeni is operated by 941 Apps, LLC dba ResumeGeni — the same studio Blake Crosley runs. Blake spent twelve years at ZipRecruiter, most recently as VP of Product Design, where he designed interfaces used by more than 110 million job seekers. The full origin story is on his founder portfolio at blakecrosley.com/work/resumegeni.

Which AI model does ResumeGeni use?

Anthropic's Claude Opus, the most capable model in Anthropic's family. The studio uses Opus exclusively for user-facing AI calls; cheaper models produce cheaper output, and the product competes on quality, not throughput.

How does ResumeGeni know what each ATS expects?

From testing. The product was built on a corpus of real job listings and real ATS parsing behaviors, not on generic resume advice. Per-ATS guides for Workday, Greenhouse, Taleo, iCIMS, and Lever live in the ResumeGeni blog and document the exact parsing quirks the optimizer respects.

What can I export from ResumeGeni?

Microsoft Word (.docx) and PDF, in three template styles — Minimal, Executive, and Modern. Both formats are designed to parse reliably across all major ATS platforms.

Does ResumeGeni support languages other than English?

Yes. Seventy-seven languages, including full resume translation and locale-aware formatting for country-specific resume norms (length, photo expectations, personal-information conventions). The translation layer is built on the same Claude Opus model that powers the ATS optimizer.

What's the tech stack?

FastAPI on the backend, HTMX and Alpine.js on the frontend, Jinja2 templates, Supabase Postgres, Stripe for payments, Anthropic Claude for AI calls. The same no-build server-rendered stack the studio uses on every product. Ship fast, measure everything, iterate on evidence.

Where is the personal case study?

Blake's founder portfolio piece on ResumeGeni — the ZipRecruiter background, per-ATS engineering breakdown, design principles, and what he learned building it — lives at blakecrosley.com/work/resumegeni. This page is the studio's product overview.