Applied AI Engineer — Evaluation & Benchmarking

Sable; San Francisco (CA); On-site; USD 140,000 - 190,000; Full time

Job summary

Sable is seeking an engineer to translate performance signals into clear evaluation criteria for Aidan, the AI agent that leads customer calls. You will design experiments across voice, vision, and browser interactions, and drive improvements to the agent, context, and models in a real product environment.

You will build benchmarks and simulations, score customer-specific scenarios, and identify gaps in capabilities to accelerate the next generation of intelligent assistants.

Qualifications

• Engineer with statistics and/or applied machine learning experience.
• Comfortable in a production codebase.
• Bonus: prior experience with evaluations or with voice, realtime, or browser use/computer use agents.

Responsibilities

• Design evaluations for voice, vision, and browser use to direct and accelerate improvements in the agent, context, and models.
• Build and maintain our internal benchmarks and simulations.
• Work on systems to score customer-specific scenarios and identify gaps in current capabilities.

Skills

Machine learning

Statistics

Production codebase

Job description

Sable is seeking an engineer to translate performance signals into clear evaluation criteria for Aidan, the AI agent that leads customer calls. You will design experiments across voice, vision, and browser interactions, and drive improvements to the agent, context, and models in a real product environment.

You will build benchmarks and simulations, score customer-specific scenarios, and identify gaps in capabilities to accelerate the next generation of intelligent assistants.