Full-Stack ML Engineer: Build GPU-Powered AI Pipelines

Scenario; United States; On-site; USD 150,000 - 230,000; Full time

Job summary

Scenario is seeking a hands-on ML/AI platform engineer to integrate and serve GPUs-based models—image, video, 3D, audio and text—from open‑source weights or external APIs behind a single interface. You will own training and fine-tuning pipelines and the processing layer for captions, upscaling, and rendering in production.

You’ll tune compute, manage latency and cost, patch model libraries, and push model integration into the cloud API and SDK.

Qualifications

• Proven Python fluency and experience shipping ML in production.
• Ability to deploy models on GPUs with focus on latency and cost budgets.
• Experience with open-source model code and fixing integrations in PRs.
• Clear written English and ability to work in a global ML-native workflow.

Skills

Python

ML ecosystem

GPU deployment

Latency optimization

Open-source PRs

Model integration

Tools

Transformers

Diffusers

Flux

Job description

Scenario is seeking a hands-on ML/AI platform engineer to integrate and serve GPUs-based models—image, video, 3D, audio and text—from open‑source weights or external APIs behind a single interface. You will own training and fine-tuning pipelines and the processing layer for captions, upscaling, and rendering in production.

You’ll tune compute, manage latency and cost, patch model libraries, and push model integration into the cloud API and SDK.