🛠 Tech Stack

💼 About This Role

You'll design and implement a scalable self-serve evaluation platform for a frontier AI company. Your work will directly power experimentation and quality for building AGI. This role offers fully remote work across Europe and North America.

🎯 What You'll Do

• Design a Python framework for centralized benchmark implementation
• Build and maintain distributed evaluation pipelines at scale
• Collaborate with modeling and product teams to improve tooling

📋 Requirements

• Strong engineering background with experience in software projects
• Experience building highly reliable services and distributed systems
• Experience with data pipelines, message queues, and cloud services
• Proficiency in monitoring and alerting tools like Grafana, Prometheus

✨ Nice to Have

• Experience designing frameworks or tooling for developers
• Product mindset towards building developer-facing software
• Experience with ML ops and data visualization platforms

🎁 Benefits & Perks

• 🏖️ Fully remote work & flexible hours
• ✈️ 37 days/year of vacation & holidays
• 🏥 Health insurance allowance for you and dependents
• 💰 Wellbeing and home office allowances
• 👥 Great diverse & inclusive people-first culture

📨 Hiring Process

Estimated timeline: 2-4 weeks

1. 1Intro call with Founding Engineer· 30 min
2. 2Technical Interview(s)· 60 min
3. 3Team fit call with People team· 30 min
4. 4Final interview with Founding Engineer· 45 min