🛠 Tech Stack

💼 About This Role

You'll design and run creative evaluations of new AI capabilities, turning emerging ideas into measurable experiments. Your work will help the developer ecosystem understand what actually works in AI. You'll publish results that establish better evaluation patterns for the industry.

🎯 What You'll Do

• Design evaluations of new AI capabilities
• Build datasets and scoring logic for experiments
• Create tests that expose failure modes
• Write technical posts explaining methodology

📋 Requirements

• Python programming experience
• LLM evaluation system contribution
• Experiment design comparing models or prompts

✨ Nice to Have

• Published technical blog posts
• Experience with agent or RAG evaluation
• Contributed to open-source evaluation tools

🎁 Benefits & Perks

• 🏥 Medical, dental, and vision insurance
• 🍽️ Daily lunch, snacks, and beverages
• 🌴 Flexible time off
• 💰 Competitive salary and equity
• 🤖 AI Stipend