Senior Python Engineer - AI Code Evaluation (Codex / Claude Code, up to $200/hr)
$208,000–$416,000 year
RemoteUnited States or Calgary, Alberta, Canada
Job Summary
Evaluate AI-generated coding interactions end-to-end, judging whether outputs are useful, correct, and aligned with how a strong engineer would think. Assess the quality of explanations and reasoning, distinguishing between different levels of response quality. Provide clear, opinionated feedback on what worked, what didn't, and what felt misleading. Help define what great looks like when interacting with tools like Cursor, OpenAI Codex, and Claude Code. This role focuses on engineering taste rather than syntax correctness, requiring a Staff or Principal-level engineer to make subjective but rigorous judgments about model behavior in real-world scenarios.
Required Qualifications
- Senior AI Interaction Evaluator (CodeX / Claude Code)
- Contract
- $100–$200/hour
- 10–20 hrs/week
- Start ASAP
- Through early May
- Highly experienced software engineer (SR+)
- Staff / Principal-level engineer (or equivalent experience)
- Strong background in one of the below: TypeScript / JavaScript, Python
- Hands-on experience using: OpenAI Codex, Claude Code, Cursor
- Deep familiarity with modern AI-assisted dev workflows
- Able to evaluate code without needing to fully execute or deeply review every line
- Comfortable giving direct, opinionated feedback
- High bar for what 'good engineering' looks like
- Must be able to assess the quality of explanations and reasoning, not just code
- Must be able to distinguish between different levels of response quality (e.g. what makes something a 2 vs 4)
- Must be comfortable making subjective but rigorous judgments
- Must be able to provide clear, opinionated feedback on: What worked, What didn't, What felt 'off' or misleading
- Must be able to help define what great looks like when interacting with tools like Cursor
- Must be able to judge whether outputs are: Useful, Correct (at a high level), Aligned with how a strong engineer would think
- Must be able to assess whether the response makes sense
- Must be able to assess whether the preamble and reasoning are useful
- Must be able to assess whether the output reflects strong engineering judgment
- Must be able to assess whether the interaction feels right to an experienced developer
- Must be able to judge whether the model thinks like a great engineer
- Must be able to judge whether the model is guiding the user well, or just dumping output
- Must be able to judge whether the interaction would build or erode trust
- Must be able to 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?
Desired Qualifications
- Experience with tools like Cursor or similar AI-first IDEs
- Prior exposure to prompt design or evaluation workflows
- Experience mentoring senior engineers or defining engineering standards
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.