🛠 Tech Stack

💼 About This Role

You'll build and operate backend systems powering AI features in a proactive AI chat app. You'll design inference pipelines and orchestration layers, owning production reliability and performance. This role sits between models and users, where latency and correctness directly impact real-world experiences.

🎯 What You'll Do

• Design and operate inference pipelines and orchestration layers
• Own production monitoring, logging, alerting, and incident response
• Optimize latency and throughput across caching and streaming
• Build stable APIs for mobile and desktop clients

📋 Requirements

• Backend engineering fundamentals in production environments
• Experience running high-throughput, low-latency services
• Familiarity with AI inference patterns (LLMs, embeddings, multimodal)

✨ Nice to Have

• Experience with Python and Node.js
• Experience with Kubernetes and Docker

🎁 Benefits & Perks

• 🚀 High autonomy and ownership
• 💡 World-class team with high talent density
• 📈 Rapid iteration and learning

📨 Hiring Process

3-4 interviews via virtual or onsite, with prompt decision.

🚩 Heads Up

• Title includes 'Senior' but experience not explicitly stated; estimated based on inference from role complexity.