Lamr: AI Job Search Workspace

I led product design for Lamr, an AI-powered job application tracker that brings role discovery, fit evaluation, tailored documents, application tracking, and interview preparation into one focused workflow.

1. Replace fragmented job-search tools with a single, context-rich workspace.

2. Help users evaluate opportunities before investing time in an application.

3. Make tailored resumes and cover letters faster to create without making them feel generic.

4. Reduce cognitive load with a clear pipeline, useful AI assistance, and durable job context.

5. Build a flexible foundation for future career-support workflows.

I led product design across the Lamr experience, shaping the product model, information architecture, interaction patterns, and visual direction for AI-assisted job-search workflows.

My responsibilities included product design strategy, UX architecture, pipeline and job-detail design, AI-assisted screening and document-generation flows, visual-system direction, responsive UX, and implementation collaboration.

Founding Product Designer and part of the core team at Lamr, working with the product and engineering team.

A serious job search is rarely managed in one place. People move between job boards, spreadsheets, browser tabs, notes, resume versions, email threads, and AI tools, often reconstructing the same context for every application.

The issue is not only organizational. Each opportunity requires a series of decisions: Is this role worth pursuing? Which experience is most relevant? What has already been sent? What should happen next?

Most existing tools solve only one part of the workflow. Trackers help users log applications. Resume builders help them make documents. Generic AI tools can generate text, but rarely retain the job-specific context needed to make that output useful.

The design challenge was to create an operating system for the job search: a product that supports administration, prioritization, writing, and preparation without becoming another system to maintain.

I mapped the recurring journey from opportunity to decision:

Discover → Save → Evaluate → Tailor → Apply → Follow up → Interview → Decide

This revealed a key product insight: the job itself, not the spreadsheet or document, should be the organizing unit of the experience.

Every application became a dedicated workspace containing the original job description, application status, fit signals, tailored materials, notes, follow-ups, interview questions, and preparation content.

This structure reduced context switching and created a more useful role for AI. Instead of placing AI in a separate chat interface, I designed it into the moments where users already need support: understanding a role, identifying relevant experience, drafting materials, and preparing for the next stage.

The principle was simple: AI should improve judgment and reduce repetitive work, while the user remains in control of every important decision.

The primary experience is a clear application pipeline that makes progress visible at a glance. Each role moves through meaningful stages: Draft, Generated, Applied, Interview, Offer, and Rejected. Distinct color cues help users quickly understand momentum and next actions.

Within a job, the interface becomes a focused working environment:

• A structured job-description view preserves the original source while making long postings easier to read.

• Match screening surfaces alignment between the role and a user's experience.

• Resume and cover-letter workflows use saved preferences and job context to produce stronger starting points.

• Notes, questions, and interview preparation remain attached to the opportunity rather than scattered across separate tools.

• Document previews and PDF output support the final step from draft to application-ready material.

The visual system was designed to feel calm, direct, and editorial. Spacious layouts and restrained surfaces reduce noise; vivid color is reserved for meaningful states such as progress, urgency, and outcomes.

Lamr transforms job searching from a collection of disconnected tasks into one intentional workflow.

The product helps users keep every opportunity, decision, document, and next step connected, making it easier to maintain momentum during a process that is often high-volume and emotionally demanding.

Early product benchmarks showed the value of combining tracking and AI-assisted workflows in one place:

The project demonstrates my approach to senior product design: understand the behavior behind the problem, design the system rather than isolated screens, and use AI where it creates clear, measurable utility.