🛠 Tech Stack

💼 About This Role

You'll design and scale the intelligent nervous system of Coupang's AI platform, building orchestration and routing layers for LLMs and foundation models. Your work will ensure high availability, low latency, and cost efficiency across thousands of accelerators. This role offers a unique opportunity to shape the infrastructure powering one of the fastest-growing e-commerce companies.

🎯 What You'll Do

• Design load-balancing algorithms for AI workloads
• Architect inference orchestration with auto-scaling
• Minimize tail latency using batching and caching
• Build infrastructure-as-code pipelines for dynamic fleets

📋 Requirements

• 8–12 years of software engineering experience
• Proficiency in Go or Python
• Expert-level knowledge of Kubernetes internals
• Experience with load balancing and request routing

✨ Nice to Have

• Experience with LLM inference infrastructure
• Familiarity with mixed precision and kernel tuning
• Multi-cloud deployment experience (AWS, Azure, GCP)

🎁 Benefits & Perks

• 🏖️ Unlimited PTO
• 💰 Equity participation
• 🏥 Comprehensive health insurance
• 📚 Learning and development budget

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Screen· 30 min
2. 2Technical Interview· 60 min
3. 3System Design Interview· 60 min