🛠 Tech Stack

💼 About This Role

You'll build the core agent harness that makes Codex agents dependable in production, working across the stack from Rust systems code to LLM inference and sandboxed execution. This role sits close to research and shapes how models are trained and evaluated.

🎯 What You'll Do

• Design and build the core agent harness and execution loop
• Build sandboxing, orchestration, and workflow infrastructure
• Develop evaluation and debugging systems for agent performance
• Run ablations to improve solve rate, latency, and cost

📋 Requirements

• Production systems experience in distributed systems or infrastructure
• Hands-on experience with LLM applications or coding agents
• Ability to debug across Rust systems code and Python configuration layers
• Care about reliability and debuggability

✨ Nice to Have

• Deep Rust and sandboxing experience
• Background in compilers or inference optimization
• Open-source infrastructure work

🎁 Benefits & Perks

• 💰 Competitive salary ($230K–$385K) plus equity
• 🏖️ Flexible PTO
• 🏥 Comprehensive health coverage
• 🍱 Daily meals at office
• 📈 Learning and development budget

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Call· 30 min
2. 2Technical Interview· 60 min
3. 3Onsite (Virtual)· 4 hours