Staff Software Engineer, Machine Learning (Computer Vision)

About this role

About DeepWalk

DeepWalk is a fast-growing venture that helps cities keep people safe using computer vision to map and monitor their sidewalks. We have ongoing contracts with cities, universities, and engineering firms.

In the past year, we’ve processed thousands of miles of sidewalk across 20+ states, generating millions of labeled data points used in real-world infrastructure decisions. We’ve raised $4.1M, recently closed a $2.1M seed round led by Enable Ventures, and we currently generate 7-figure revenue helping communities across America.

Staff Software Engineer — Computer Vision Platform

$150,000 – $190,000 base salary + equity · Hybrid (Chicago)

We’re hiring a Staff Software Engineer to lead the technical direction of DeepWalk’s computer vision platform for automated sidewalk inspection. This role is focused on tackling high-impact, open-ended problems around large-scale imagery, production ML systems, and data pipelines that handle hundreds of terabytes of data. We’re specifically looking for engineers who have built and operated computer vision or ML systems in production at scale (not just research or prototyping).

You’ll play a key role in how we process, analyze, and deliver insights from millions of images, supporting cities as they work to build safer, more accessible infrastructure.

In this role, you’ll work closely with a handful of experienced engineers, help set technical direction, and establish patterns the team can scale with.

Our core stack today includes Python-based CV/ML systems running on AWS, with data pipelines and services designed to handle large volumes of imagery and geospatial data.

What You’ll Do

As a Staff Engineer at DeepWalk, you’ll have significant ownership over both the systems we build and how we build them. You will…

• Own the lifecycle of our computer vision models, including training, evaluation, deployment, and iteration
• Improve model performance in real-world conditions (noise,...