You have opted out of job matches in .
To undo this, go to the 'Skills and Interests' section of your preferences.
Shared by 
14 days ago
warning
Heads-up
Requirements and responsibilities
Contract | $50-200/hr | 10+ hrs/week | Project-basedRoles open on a rolling basis - apply to join the talent bench and we’ll reach out when one matches. Expect 40+ hrs once a project starts; timing depends on availability, but we move people in at the earliest genuine opportunity.These roles are currently filled but we hire on a rolling basis as new projects open up. Apply now to join our talent bench — qualified candidates will be contacted directly when roles become available.We’re looking for highly experienced software engineer (SR+) to help evaluate the quality of interactions with modern coding agents such as OpenAI Codex and Claude Code.This is not a traditional engineering role.You won’t be writing production code.You’ll be evaluating something harder: Whether the model thinks like a great engineer.What This Role Actually IsYou will assess how AI coding agents behave in real-world scenarios — focusing on:Whether the response makes senseWhether the preamble and reasoning are usefulWhether the output reflects strong engineering judgmentWhether the interaction feels right to an experienced developerThis role is about engineering taste — not syntax correctness.What You’ll Be DoingEvaluate AI-generated coding interactions end-to-endJudge whether outputs are:UsefulCorrect (at a high level)Aligned with how a strong engineer would thinkAssess the quality of explanations and reasoning, not just codeDistinguish between different levels of response quality (e.g. what makes something a 2 vs 4)Provide clear, opinionated feedback on:What workedWhat didn’tWhat felt “off” or misleadingHelp define what great looks like when interacting with tools like CursorWhat We Mean by “Taste”We’re specifically looking for engineers who can answer questions like:Does this feel like something a strong engineer would actually say?Is this explanation helpful, or just technically correct?Is the model guiding the user well, or just dumping output?Would this interaction build or erode trust?You should be comfortable making subjective but rigorous judgments.Who You AreStaff / Principal-level engineer (or equivalent experience)Strong background in one of the below:TypeScript / JavaScriptPythonHands-on experience using:OpenAI CodexClaude CodeCursorDeep familiarity with modern AI-assisted dev workflowsAble to evaluate code without needing to fully execute or deeply review every lineComfortable giving direct, opinionated feedbackHigh bar for what “good engineering” looks likeNice to HaveExperience with tools like Cursor or similar AI-first IDEsPrior exposure to prompt design or evaluation workflowsExperience mentoring senior engineers or defining engineering standardsEngagement DetailsUS and Canada up to $200/hrEU and Latam up to $150/hrOther locations up to $100/hr Hours: ~10–20 hours/weekDuration: Ongoing — project-basedProcess:Take-home evaluation exerciseOne behavioral interview
Optionally, you can add more information later (benefits, pre-screening questions, etc.)