Production ML Engineer – ML Infra & Inference

Canopy Labs; San Francisco (CA); On-site; USD 150,000 - 190,000; Full time

Job summary

Canopy Labs in San Francisco builds production systems to deploy and serve machine learning models in real-world applications. You will work on infrastructure that powers speech and avatar models and ship code rapidly to real users with measurable impact.

The role emphasizes building reliable backend services for model inference, containerized environments, and internal tools to monitor deployed models, in close collaboration with a small, high-ownership team.

Qualifications

• Experience with modern ML tooling (e.g. Hugging Face, PyTorch) and model serving frameworks.
• Experience building production systems around ML models, including data pipelines and inference services.
• Familiarity with infrastructure and DevOps tooling (Docker, Terraform, CI/CD such as Jenkins).

Responsibilities

• Develop backend services for model inference (e.g., FastAPI).
• Work with containerized environments and infrastructure automation.
• Build web interfaces or tools (e.g., React dashboards) to interact with deployed models.

Skills

ML tooling

Backend services

Data pipelines

CI/CD

Tools

Docker

Terraform

CI/CD

FastAPI

React

Job description

Canopy Labs in San Francisco builds production systems to deploy and serve machine learning models in real-world applications. You will work on infrastructure that powers speech and avatar models and ship code rapidly to real users with measurable impact.

The role emphasizes building reliable backend services for model inference, containerized environments, and internal tools to monitor deployed models, in close collaboration with a small, high-ownership team.