Inspiration
As students, we realized that tailoring a résumé for every internship posting is crucial—yet extremely time-consuming, especially when résumés are written in LaTeX. Recruiters and ATS systems often search for keywords, but students rarely update their résumé for each application. We wanted a tool that makes personalization effortless while preserving the clean, professional LaTeX formatting students love.
What it does
Our platform automatically analyzes an internship description, extracts core skills and requirements, and then rewrites, reorganizes, and enhances a student’s LaTeX résumé to better match the role.
It highlights relevant projects and experiences
Infuses missing but truthful keywords
Reorders sections based on job priorities
Generates a clean, compilable LaTeX file ready for submission
Think: ATS-optimized, role-specific LaTeX résumés in seconds.
How we built it
Built a backend pipeline using LLM-powered NLP models to parse job descriptions and extract weighted skills, tools, and responsibilities.
Created a résumé-mapping engine that pairs the user’s existing experiences to job requirements, boosting relevance while preserving authenticity.
Used LaTeX templating + automatic diffing to regenerate clean, error-free LaTeX code.
Developed a lightweight web UI where users upload résumés and paste job descriptions.
Integrated a preview-and-download compiler so students can see the PDF instantly.
Challenges we ran into
Maintaining LaTeX syntax correctness after AI-generated edits—small formatting errors used to break compilation.
Ensuring the model adds relevant keywords without “hallucinating” roles or experiences the student never had.
Balancing ATS optimization with human readability, avoiding keyword stuffing.
Creating a universal parser that handles dozens of LaTeX résumé styles and environments.
Accomplishments that we're proud of
Building a system that outputs 100% compilable LaTeX every time—no broken environments, no missing braces.
Achieving résumé tailoring that actually increases job-match scores in internal ATS tests.
Designing an intuitive workflow where students go from generic résumé → tailored version in under 20 seconds.
Positive feedback from early testers who received more recruiter responses using the optimized versions.
What we learned
Fine-grained control over LaTeX generation is essential—LLMs need guardrails, templates, and syntax-aware post-processors.
Students often undersell their experiences; good prompting and extraction can surface hidden strengths.
Tailoring isn’t just about adding keywords—contextual alignment (ordering, phrasing, emphasis) matters more.
Building trust requires transparency: students appreciate seeing exactly what changed and why.
What's next for GetHired.ai
Support for multiple LaTeX templates and dynamic theme switching.
A “résumé health score” that flags weak bullet points and suggests quantified improvements.
Version control & résumé history so users can track changes over time.
Integration with LinkedIn, Handshake, and Indeed to auto-import job postings.
A cover letter auto-tailoring module using the same job-matching engine.
Data-driven insights to help students understand which résumé versions perform best.
Built With
- claude