Media Generation Engineer — Client-Facing Pipelines

Artificial Analysis; San Francisco (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

Artificial Analysis is hiring a Forward Deployed Engineer to own our media generation benchmarking pipeline end to end in San Francisco. You’ll run image and video evaluations, manage human studies, and act as the technical face to model providers, ensuring results and methodology are clear and reliable.

You’ll work in a process-driven, deployment-focused role, collaborating with leading AI labs and enterprises, and contributing to benchmark design, data pipelines, and publication quality.

Qualifications

• 3+ years in a client-facing technical role such as solutions engineering or technical consulting.
• Strong Python proficiency and ability to navigate large, unfamiliar codebases.
• Hands-on experience with AI model APIs for image/video generation.
• Excellent debugging skills across APIs, data pipelines and code.
• Clear written and verbal English communication for technical stakeholders.
• Highly responsive, reliable, and capable of owning customer issues.
• Comfort with repeatable, quality-focused operational work.

Responsibilities

• Generate image and video outputs across models using standardized evaluation protocols.
• Set up and manage human preference studies with design and quality control.
• Process and analyze preference vote data to produce benchmark results.
• Oversee end-to-end pipeline from prompt execution to published results.
• Serve as technical contact for providers, explaining methodology and addressing queries.
• Monitor data quality, flag anomalies, ensure consistency across rounds.
• Maintain documentation of processes and configurations.
• Stay current with new image and video model releases.

Skills

Python proficiency

Client-facing experience

AI model APIs

Debugging skills

English communication

Ownership and reliability

Operational mindset

Tools

Python

AI model APIs

Job description

Artificial Analysis is hiring a Forward Deployed Engineer to own our media generation benchmarking pipeline end to end in San Francisco. You’ll run image and video evaluations, manage human studies, and act as the technical face to model providers, ensuring results and methodology are clear and reliable.

You’ll work in a process-driven, deployment-focused role, collaborating with leading AI labs and enterprises, and contributing to benchmark design, data pipelines, and publication quality.