AI Engineer

Work Location – Hybrid role in Sandy, UT

Position Overview

We’re looking for an AI Engineer who gets genuinely excited about solving real problems with AI. Not someone who just wants to chase the latest models because they’re new and shiny—we want someone who asks “what will actually make workers safer?” and “what will help safety managers prevent incidents before they happen?”

This isn’t demo work. You’ll be shipping features that construction superintendents use every morning to figure out where they need to be. Features the frontline needs in emergencies. Features that Spanish-speaking crews use to report what they’re seeing in their own words. Your work directly impacts whether someone goes home safe at the end of their day.

What you'll actually be doing:

Leading our workflow architecture

• We need to migrate our AI workflows to N8N and build something that’s actually robust and scalable, not the patchwork of tools we’ve been using

• You’ll design the workflow orchestration that connects our various AI models, data sources, and business logic in a way that makes sense

• Build workflows that are observable and self-healing, because they need to scale with us as we grow quickly

Making our NLP better

• Our conversational AI lets workers create safety reports just by talking—in English or Spanish. You’ll optimize and fine-tune that experience

• We have this feature called “Ask Mojo” that turns complex safety manuals into natural conversations. It needs to get better at making sure workers get the right answer from the right document, every time

• Build context-aware understanding that knows the difference between “fall protection” on a 30-story building versus a 6-foot ladder—because that context really matters

Pushing our OCR and computer vision forward

• Our Flex PTP technology extracts structured data from any safety form, whether it’s a pristine PDF or a mud-stained piece of paper photographed at sunset on a jobsite. We need to make this even better

• Improve accuracy on handwriting recognition, checkbox detection, form field extraction—all across wildly inconsistent formats

• Build intelligence that doesn’t just extract text but actually understands what it means in a safety context

Collaborating across the team

• Work with product managers to turn user pain points into technical solutions that actually solve problems

• Partner with other engineers to make sure your AI models integrate smoothly into the broader platform

• Talk directly to customers sometimes to understand their challenges and make sure what you’re building actually works for them

What makes you a great fit:

You’ve actually shipped AI to production

• You know the difference between a model that’s 95% accurate in testing and an 85% accurate model that users actually trust in the real world

• You’re comfortable across the full stack—from training models to designing APIs to orchestrating workflows

• You write code that other engineers want to maintain (or at least don’t hate maintaining)

You care more about impact than the technology itself

• You get excited about solving a real problem imperfectly rather than building a perfect solution to the wrong problem

• You measure success by what users can do, not just by model metrics

• You’re totally fine using “boring” technology if it’s the right tool for the job

You’re a self-starter who can handle ambiguity

• You don’t wait around for perfectly specified requirements. You talk to users, figure out the core problem, propose solutions, and execute

• You can make technical decisions with incomplete information and then adjust as you learn more

• Someone can give you a vague goal like “make our OCR work better on handwritten forms” and you’ll turn that into a concrete plan with actual milestones

You obsess over the right details

• You care about latency because a 2-second response time is the difference between a worker using your feature or avoiding it completely

• You think deeply about error handling because a confusing error message on a construction site isn’t just annoying—it creates real safety risk

• You design for actual conditions: poor lighting, people wearing gloves, limited connectivity, multilingual users

You communicate clearly

• You can explain complex technical stuff to product managers, customers, and executives in a way they understand

• You write documentation that helps your teammates understand not just what your code does, but why you built it that way

• You’re not precious about your ideas—you care more about being effective than being right

What you need to have:

Must haves

• 3+ years building and deploying AI/ML systems that actually run in production

• Strong Python skills and experience with modern ML frameworks like TensorFlow or PyTorch

• Real NLP experience—whether that’s fine-tuning LLMs, prompt engineering, RAG, or classical NLP approaches

• Hands-on work with computer vision and OCR (OpenCV, Tesseract, modern vision models, document AI services)

• Workflow automation experience with N8N is our primary tool

• Solid software engineering fundamentals: version control, testing, CI/CD, monitoring, observability

Nice to haves

• Experience with document understanding problems—forms, invoices, receipts, scanned documents, that kind of thing

• Multilingual NLP experience, especially the challenges that come with building for Spanish/English bilingual users

• Background in highly regulated industries where accuracy and compliance actually matter (construction, healthcare, finance)

• Experience with mobile-first or field-worker applications where connectivity is spotty and usability constraints are very real

• Open source contributions or side projects that show how you think about problems

• You’ve been at a growth-stage startup before where you had to wear multiple hats

• API design and integration—you’ve built systems that reliably connect multiple services

Why this role is different:

The stakes are real. Your work doesn’t just move engagement metrics—it prevents injuries. When your OCR accurately extracts a permit, when your NLP correctly understands a hazard report, when your workflow gets critical information to the right person fast enough—real people are safer because of what you built.

You’ll have real ownership. We’re small enough that you’ll see the direct impact of your work. You’ll talk to users. You’ll influence the product roadmap. You’ll make architectural decisions that define how we scale over the next few years.

The timing is perfect. We’re at the most exciting phase of a company’s life—we’ve proven the concept, we have product-market fit, and now we’re scaling. You’ll help build the technical foundation for our next stage of growth, and you’ll grow right along with us.

The problems are genuinely hard. Extracting meaningful structure from unstructured chaos. Understanding natural language in a specialized domain. Building AI that construction workers actually want to use. You’ll have the autonomy to explore new approaches when they make sense.

The mission matters. Everyone here cares deeply about worker safety. Construction alone accounts for 20% of workplace fatalities. We’ve talked to workers who’ve been injured. We’ve met safety managers who feel helpless watching preventable incidents happen. This isn’t abstract for us—we’re here to fix it.