C# Senior Engineer - AI Interaction Evaluator

Role overview A part-time contracted evaluator position assessing the quality of interactions produced by AI coding agents, with emphasis on whether they reflect the reasoning and instincts of a senior C# engineer. The role is not a traditional engineering position; instead of writing production code, the evaluator judges how well the AI behaves like an experienced .NET developer across realistic scenarios. It is suited to senior engineers who want to influence the standard for AI-assisted development through flexible, async work.

Responsibilities - Review full AI coding interactions end-to-end, weighing usefulness, high-level correctness, and alignment with senior-level engineering judgment in C# contexts. - Evaluate the quality of explanations, preambles, and reasoning rather than just the code surface. - Calibrate scoring by articulating the differences between weak and strong responses. - Deliver direct, opinionated written feedback describing what succeeded, what missed, and what felt misleading. - Help codify what an excellent interaction looks like inside AI-first IDEs and coding workflows.

Requirements - Senior- or staff-level engineering background with substantial, current C# experience across application or platform work. - Hands-on familiarity with modern AI coding tools such as OpenAI Codex, Claude Code, and Cursor-class editors. - Ability to evaluate code and conversation quality without needing to execute or audit every line. - Comfort making rigorous subjective calls about engineering taste and technical communication. - High personal standard for what good C# engineering looks like in practice.

Nice to have - Prior exposure to prompt design, evaluation pipelines, or human annotation workflows. - Experience mentoring senior engineers or defining engineering quality standards across a team.

Benefits and work setup - Contract role running through early May, with possible extension. - Roughly 10 to 20 hours per week, fully remote and flexible. - Hourly compensation between $100 and $200, with an ASAP start date. - Process includes a take-home evaluation exercise followed by a single behavioral interview.