Remote Electronics Engineer & AI Evaluation Expert

DataAnnotation; Chicago (IL); Remote; USD 55,000 - 172,000; Full time

Benefits offered by this job

Flexible work arrangements

Remote work

Project-based opportunities

Job summary

DataAnnotation seeks an experienced Electrical Engineer to assess how frontier AI models perform on real electrical and electronics tasks. You bring years of hardware design, debugging, and shipping experience, while we provide problems that push AI to reason about circuits, systems, and physical constraints.

You will design challenging problems, run them through frontier AI models, and judge outputs against professional standards.

Qualifications

• 2+ years of industry experience in circuit or electronics engineering.
• Background in electrical/electronics engineering or closely related discipline.
• Ability to defend component-level and system-level decisions.
• Ability to articulate why an answer is wrong, not only that it is.
• Familiarity with AI tools or willingness to learn quickly.

Responsibilities

• Design challenging, realistic engineering problems for frontier AI models.
• Run problems through frontier AI models and judge output against professional standards.
• Compare model versions on identical prompts and evaluate performance.
• Critique model-generated derivations, schematics, and calculations with detailed reasoning.
• Flag concrete failures with evidence such as sign errors, unphysical results, or misinterpretations.

Skills

Circuit analysis

Electrical engineering

AI tools familiarity

English language

Education

Bachelor’s degree in Electrical Engineering or related

Tools

AI tools

Job description

DataAnnotation seeks an experienced Electrical Engineer to assess how frontier AI models perform on real electrical and electronics tasks. You bring years of hardware design, debugging, and shipping experience, while we provide problems that push AI to reason about circuits, systems, and physical constraints.

You will design challenging problems, run them through frontier AI models, and judge outputs against professional standards.