Sable
Applied AI Engineer, Evals
San Francisco · On-site · Full-time · Posted Sep 15, 2026
About the job
Designs and runs evaluations of Aidan’s voice, vision, and browser-use capabilities, then uses results to improve the agent, its context, and its models.
What you'll do
- Design evaluations to guide improvements in the agent, context, and models.
- Build and maintain internal benchmarks and simulations.
- Develop systems to score customer-specific scenarios and identify capability gaps.
What they ask for
- Engineering experience with statistics and/or applied machine learning.
- Comfort working in a production codebase.
Nice to have
- Prior experience with evaluations.
- Experience with voice, realtime, or browser-use/computer-use agents.
AI focus
Evaluates and improves an AI agent that uses voice, vision, and browser interactions; work includes benchmarks, simulations, and scoring customer-specific scenarios.
Model-written summary · the original posting is authoritative