Staff Software Engineer owning OAuth, authorization, and agent delegation systems. Building governed identity infrastructure for Redpanda’s enterprise AI data platform.
About the role
- Senior software engineer evaluating Codex, Claude Code, and Cursor interactions for G2i’s engineering team. Providing rigorous feedback on AI reasoning, code quality, and developer trust.
Responsibilities
- Evaluate the quality of interactions with modern coding agents such as OpenAI Codex and Claude Code
- Assess whether AI-generated responses make sense and whether preambles and reasoning are useful
- Judge whether outputs demonstrate strong engineering judgment
- Evaluate AI-generated coding interactions end to end
- Determine whether outputs are useful, correct at a high level, and aligned with strong engineering practice
- Assess explanations and reasoning, not just code
- Distinguish between different levels of response quality
- Provide clear, opinionated written feedback on what worked, what did not, and what felt misleading
- Help define what excellent interaction quality looks like for Cursor, Codex, and Claude Code
- Record short video explanations of evaluations
- Complete a take-home evaluation exercise before starting
Requirements
- Senior, Staff or Principal-level engineer (or equivalent experience)
- Strong background in TypeScript/JavaScript or Python
- Hands-on experience with at least one of OpenAI Codex, Claude Code or Cursor
- Deep familiarity with modern AI-assisted development workflows
- Ability to evaluate code without executing it or reviewing every line
- Strong written and spoken English (B2 or above)
- Ability to write detailed feedback and record short video explanations
- Comfortable giving direct, opinionated feedback
- High standards for engineering quality
- Prior exposure to prompt design or evaluation workflows is nice to have
- Experience mentoring senior engineers or defining engineering standards is nice to have
- Must clear a take-home evaluation exercise with a recorded Loom walkthrough
- Must agree to a simple background check for the project
Benefits
- Flexible 10–20 hours/week
- Ongoing project opportunities for evaluators who perform well
- Flexible engagement hours
- Opportunity to work on projects lasting from about two weeks to a few months
Job title
Job type
Experience level
Salary
Degree requirement
No Education Requirement
Tech skills
Location requirements
Report this job
Found something wrong with the page? Please let us know by submitting a report below.
Senior software engineer evaluating AI coding agents for G2i’s engineering team. Assessing reasoning, explanations, and engineering judgment in Codex, Claude Code, and Cursor interactions.
Senior software engineer evaluating AI coding agents such as Codex, Claude Code, and Cursor. Providing rigorous written and video feedback on engineering quality.
Senior software engineer evaluating Codex, Claude Code, and Cursor interactions. Providing rigorous written and video feedback on AI - generated coding quality for G2i.
Senior engineer evaluating Codex, Claude Code, and Cursor interactions for G2i. Providing rigorous written and video feedback on AI - generated engineering work.
Applied AI Lead deploying Heidi’s healthcare AI for strategic healthcare accounts. Driving adoption, expansion, renewal, and measurable clinical and operational value.
Software Engineer, AI building secure, production - ready LLM and cloud - native solutions for Softchoice, an IT solutions provider. Delivering RAG, APIs, automation, and enterprise AI integrations.
Full - stack developer building TypeScript AI customer - support agents for gaiia’s telco operating system. Developing agent runtimes, omnichannel integrations, evaluation tooling, and safety guardrails.
Senior AI Engineer embedding with clinical, product, and operations teams. Shipping validated, monitored AI features for Prenuvo’s proactive whole - body healthcare platform.
Backend Software Engineer creating realistic coding challenges, bug fixes, and deterministic verifiers for Gramian’s AI training projects. Evaluating backend code quality, reliability, testing, and performance.