G2i Inc.

Evaluator

• Evaluate AI-generated coding interactions end-to-end
• Judge whether outputs are:
• - Useful
• - Correct (at a high level)
• - Aligned with how a strong engineer would think
• Assess the **quality of explanations and reasoning**, not just code
• Distinguish between different levels of response quality (e.g. what makes something a *2 vs 4*)
• Provide clear, opinionated feedback on:
• - What worked
• - What didn’t
• - What felt “off” or misleading
• Help define what *great* looks like when interacting with tools like Cursor

AI Interaction Evaluator, Codex / Claude Code

Frontend Engineer

• Design, develop, and maintain scalable full-stack applications using React.js, Node.js, and TypeScript.
• Integrate LLMs and AI services into production features — structured outputs, retrieval-augmented generation (RAG), and agentic or tool-using workflows.
• Build and maintain the supporting data and retrieval layers for AI features (embeddings, vector search, context pipelines).
• Measure and improve AI feature quality, reliability, latency, and cost through evaluation and guardrails.
• Collaborate with cross-functional teams to define, design, and ship new features.
• Implement best practices for platform engineering, performance optimization, and security.
• Work closely with DevOps to automate and streamline deployment processes.
• Write clean, testable, and efficient code, and participate in code reviews.
• Stay current with emerging AI and web technologies and share knowledge with peers.

AI Interaction Evaluator, Codex / Claude Code

Full Stack Engineer – AI-Native, React, Node