AI Evaluation Engineer — Review Coding Tasks

Remote Jobs; United States; Remote; USD 114,341,000 - 137,760,000; Full time

Job summary

Terac is conducting a paid study to evaluate coding tasks used for AI agent evaluation. Our team is building a suite of programming environments to test complex software capabilities and ensure frameworks are realistic, accurate, and well calibrated.

We are seeking software engineers in the United States with experience building, reviewing, or testing evaluation harnesses and coding tasks. Candidates should be comfortable discussing technical architectures and providing actionable feedback on

Qualifications

• Professional software engineer with strong technical background.
• Experience building or reviewing evaluation harnesses and coding tasks.
• Comfortable discussing technical architectures and evaluation frameworks.

Responsibilities

• Review realistic programming tasks designed for AI evaluation.
• Assess the accuracy and structure of various evaluation harnesses.
• Walk us through your thought process while checking code validity.
• Provide actionable feedback on how to improve task complexity and realism.

Skills

Software engineer

Eval harness familiarity

Job description

Terac is conducting a paid study to evaluate coding tasks used for AI agent evaluation. Our team is building a suite of programming environments to test complex software capabilities and ensure frameworks are realistic, accurate, and well calibrated.

We are seeking software engineers in the United States with experience building, reviewing, or testing evaluation harnesses and coding tasks. Candidates should be comfortable discussing technical architectures and providing actionable feedback on