Job Description
Contract | Remote, worldwide | $100-$200/hour depending on experience and location | ***** hrs/week
n
Check out this Loom video for more details:
share/b0d1b0bf24c44ae8b95dca84b9db60e5
n
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.
n
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 is
n
You will assess how AI coding agents behave in real-world scenarios, focusing on:
n
n
Whether the response makes sense
n
Whether the preamble and reasoning are useful
n
Whether the output reflects strong engineering judgment
n
Whether the interaction feels right to an experienced developer
n
n
This role is about engineering taste. Syntax correctness is the easy part.
What you'll be doing
n
n
Evaluate AI-generated coding interactions end to end
n
Judge whether outputs are useful, correct at a high level, and aligned with how a strong engineer would think
n
Assess the quality of explanations and reasoning, not just the code
n
Distinguish between levels of response quality (what makes something a 2 vs a 4)
n
Give transparent, opinionated feedback in writing on what worked, what didn't, and what felt off or misleading
n
Help define what great looks like when working with tools like Cursor, Codex and Claude Code
n
What we mean by "taste"
n
n




Does this feel like something a strong engineer would actually say?
n
Is this explanation helpful, or just technically correct?
n
Is the model guiding the user well, or just dumping output?
n
Would this interaction build or erode trust?
n
n
You should be comfortable making subjective but rigorous judgments, and explaining them clearly.
Who you are
n
n
Senior, Staff or Principal-level engineer (or equivalent experience)
n
Strong background in
TypeScript/JavaScript
or Python
n
Hands-on experience with at least one of OpenAI Codex, Claude Code or Cursor
n
Deep familiarity with modern AI-assisted dev workflows
n
Able to evaluate code without executing it or reviewing every line
n
Strong written and spoken English (B2 or above). You'll be writing detailed feedback and recording short video explanations, so this is a hard requirement
n
Comfortable giving direct, opinionated feedback
n
High bar for what good engineering looks like
n
Nice to have
n
n
Prior exposure to prompt design or evaluation workflows
n
Experience mentoring senior engineers or defining engineering standards
n
Engagement details
n
n
Rate: $100-$200/hour depending on experience and location
n
Hours: ***** hours/week, flexible
n
Duration: ongoing. Projects run from about two weeks to a few months each, and we offer new ones to evaluators who do well
n
Start: as soon as you clear the take-home and a project has an open seat
n
Process: one take-home evaluation exercise with a recorded Loom walkthrough. No interview
n
#J-*****-Ljbffr

📌 Senior Software Engineer, Ai Training - Au (Melbourne)
🏢 G2i
📍 Melbourne