Software Engineer, Machine Learning Operations

Blissway Inc.•Denver, CO

3d•Onsite

About The Position

Blissway is a startup that simplifies toll collection and dramatically improves highway safety. We are multiple startups in one: Deep Tech, AI/ML, Hardware, SaaS, and IoT. For the past five years, we have built a nearly insurmountable technological lead in tolling, an industry that is quietly bigger than football. While our competitors have thousands of employees, we operate with a lean but growing team of less than 30. We’ve stayed under the radar, but our impact is visible on the massive Interstate Highway System connecting every major US metro (except Juneau, AK—sorry, Juneau). You are a good fit if... You love the grind: You take ownership and put in the time to meet deadlines. Our recent team survey showed an average of 55 hours/week, with occasional 70+ hour bursts for major releases. You are detail obsessed: You have experience writing code, designing or building systems that stands up to the unpredictability of the physical world, where the small details are the difference between success and failure. You are adaptable: We are a lean team. If you only want to work on a "niche thing" or are uncomfortable helping other teams when they need a boost, this isn't the place for you. We expect you to figure out what you need to get stuff done. You code really well: We mostly use Python and TypeScript, but we don’t care what you’re most proficient in today—as long as you learn fast. The Mission: You are the engineer who makes models real. At Blissway, we process 11 million images every single day, running detection, segmentation, classification, embeddings, and re-identification across everything in the camera's frame. You will own the system that makes that possible: the infrastructure, deployment, and monitoring that take a model to the road, and the updates that keep it correct once it's there. This role is for the engineer who sees a great model stuck in a notebook and can't rest until it's running reliably in production.

Requirements

Experience: 2 to 6 years of software engineering building and running production systems, such as infrastructure, backend services, or ML platforms.
Production Fundamentals: You write production-quality code and build reliable systems: pipelines, deployment, observability, and the tooling that keeps them running.
ML Curiosity: You don't need to design novel architectures. You may have deployed models before, or you may be a strong engineer who wants to go deep on ML. Either way, you understand, or are eager to learn, how models are trained and evaluated well enough to debug them in production.

Nice To Haves

Experience taking ML models past the notebook (deployment, monitoring, retraining)
Deploying to edge or resource-constrained hardware
Running your own servers instead of fully managed cloud services

Responsibilities

Own the Platform: We wire it all together and run our own servers. You own the infrastructure behind every model we ship: training and serving infrastructure, model versioning, deployment, and rollback.
Vision at Real Scale: 11 million images a day across vehicles, license plates, wheels, and lane markings, plus data from multiple other roadside sensors. At this volume, a faster pipeline or a cheaper inference path saves money every day.
Real Hardware in the Real World: We own the devices in the field, so the systems you build run on roads, not just in a test environment.
Edge and Cloud: Most of our compute lives in the cloud, where power is effectively unlimited. We're now pushing more inference onto roadside hardware, which is a completely different problem. You'll build the path that gets models onto edge devices, keeps them updated, and tells us when something drifts.
Monitor What Matters: Your job is making sure the model stays correct. You build the monitoring that catches degradation before anyone else does, and you own the updates that fix it.