ML Platform Engineer: Edge-to-Cloud Production

Blissway Inc.; Denver (CO); On-site; USD 120,000 - 180,000; Full time

Benefits offered by this job

Relocation bonus

Health coverage

401(k) match

Life & disability insurance

Equity

4 weeks PTO

Parental leave

Sabbatical

Blissway Kitchen

Snacks Autonomy

BlissTrip

Monthly events

Tuition reimbursement

Job summary

Blissway Inc. in Denver seeks an engineer to own the platform that trains, serves, and monitors ML models as they move from notebooks to production.

You will integrate training, deployment, and monitoring across edge and cloud environments to keep models accurate and robust on real roads. You’ll work across infrastructure, data pipelines, and deployment tooling to support 11 million images daily, ensuring reliability and cost efficiency while collaborating with a lean, fast-moving team in a

Qualifications

• 2 to 6 years of software engineering building and running production systems.
• Production fundamentals: production-quality code, pipelines, deployment, observability.
• ML curiosity: understanding how models are trained and evaluated to debug in production.
• Bonus: deploying ML models to edge or on own servers.

Responsibilities

• Own the Platform: manage infrastructure behind every model including training, serving, versioning, deployment, and rollback.
• Vision at Real Scale: handle 11 million images daily across vehicles, plates, wheels, and lane markings.
• Real Hardware in the Real World: run systems on roadside devices, not just tests.
• Edge and Cloud: push inference to roadside hardware and build paths to edge deployment.
• Monitor What Matters: build monitoring to detect degradation and own fixes.

Skills

Python

TypeScript

Production systems

ML deployment

Observability

Education

B.S. in CS or related

Tools

AWS

Kubernetes

Terraform

Job description

Blissway Inc. in Denver seeks an engineer to own the platform that trains, serves, and monitors ML models as they move from notebooks to production.

You will integrate training, deployment, and monitoring across edge and cloud environments to keep models accurate and robust on real roads. You’ll work across infrastructure, data pipelines, and deployment tooling to support 11 million images daily, ensuring reliability and cost efficiency while collaborating with a lean, fast-moving team in a