Senior Software Engineer - AI Interaction Evaluator (Codex / Claude Code, up to $200/hr)

G2i
Miami, Calgary, Mississauga, Vancouver, Boston, Montreal, Denver, Oklahoma City, Nashville, Indianapolis, Chicago, Seattle, Atlanta, Ottawa, Toronto, Austin, Dallas, San Antonio, Philadelphia, Richmond, Columbus, Las Vegas, Winnipeg, Boise, Washington, Edmonton
Workplace: RemoteContractUSD 100 - 200 hourlyFunction: Software EngineeringSkills: ["Subjective but rigorous judgment","Opinionated feedback","Engineering taste"]

Evaluate AI coding agent interactions end-to-end to determine whether responses make sense, reasoning is useful, and outputs reflect strong engineering judgment. You’ll assess explanation quality and “engineering taste” rather than syntax correctness, distinguishing multiple response quality levels and providing clear, opinionated feedback. This role uses tools like OpenAI Codex, Claude Code, and Cursor and is designed for staff/principal-level engineers who can make subjective but rigorous evaluations.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
G2i
G2i
1 day ago

Senior Software Engineer - AI Interaction Evaluator (Codex / Claude Code, up to $200/hr)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 23 hours agoStatus: Live

Job Summary

Evaluate AI coding agent interactions end-to-end to determine whether responses make sense, reasoning is useful, and outputs reflect strong engineering judgment. You’ll assess explanation quality and “engineering taste” rather than syntax correctness, distinguishing multiple response quality levels and providing clear, opinionated feedback. This role uses tools like OpenAI Codex, Claude Code, and Cursor and is designed for staff/principal-level engineers who can make subjective but rigorous evaluations.
Location: Miami, Calgary, Mississauga, Vancouver, Boston, Montreal, Denver, Oklahoma City, Nashville, Indianapolis, Chicago, Seattle, Atlanta, Ottawa, Toronto, Austin, Dallas, San Antonio, Philadelphia, Richmond, Columbus, Las Vegas, Winnipeg, Boise, Washington, Edmonton
Workplace: Remote
Employment Type: Contract
Job Function: Software Engineering

Key Responsibilities

  • •Evaluate AI-generated coding interactions end-to-end.
  • •Judge whether responses are useful and correct at a high level.
  • •Assess explanation quality and reasoning, not just code.
  • •Distinguish between different levels of response quality and what makes each rating.
  • •Provide clear, opinionated feedback and help define what “great” looks like when using tools like Cursor.

Pay and Benefits

Salary: USD 100 - 200 hourly

Key Requirements

  • •Staff / Principal-level engineer (or equivalent experience).
  • •Strong background in TypeScript/JavaScript or Python.
  • •Hands-on experience using OpenAI Codex, Claude Code, and Cursor.
  • •Deep familiarity with modern AI-assisted development workflows.
  • •Comfortable making subjective but rigorous judgments and providing direct, opinionated feedback.
Experience:AI-assisted developmentCoding agentsEvaluation workflows
Skills:Subjective but rigorous judgmentOpinionated feedbackEngineering taste
Tech Stack:TypeScriptJavaScriptPythonOpenAI CodexClaude CodeCursor

Company Brief

G2i
G2i is a video-first hiring platform that connects companies with pre-vetted remote engineers (React, React Native, GraphQL, etc.) using technical screening, live interviews, and AI-assisted hiring infrastructure to speed hiring.
Industry: HR Tech
Company Size: Medium (51 to 250 employees)
Growth: Growth Stage Startup
Headquarters: Miami, United States
Founded: 2016
Glassdoor
Glassdoor: 3.3
WebsiteLinkedInGlassdoor