🛠 Tech Stack

💼 About This Role

You'll define the inference strategy and drive architectural decisions for deploying multi-modal AI models on mobile hardware. Your work will directly determine the latency, quality, and power profile of AI-driven features affecting billions of mobile game players. This hands-on role includes mentoring a team and pioneering mobile-optimized inference techniques.

🎯 What You'll Do

• Set technical vision for deploying multi-modal AI to iOS and Android
• Select and evaluate mobile inference runtimes like CoreML and TFLite
• Own end-to-end optimization pipeline from model export to kernel tuning
• Mentor ML engineers and define engineering best practices

📋 Requirements

• 8+ years in ML engineering with 3+ years on-device inference optimization
• Proven production deployment of transformer-based models on mobile hardware
• Hands-on expertise with CoreML, TFLite, ONNX Runtime, or ExecuTorch
• Expert-level command of INT8/INT4/FP16 quantization and pruning

✨ Nice to Have

• Experience shipping world-model or neural rendering pipelines on mobile
• Contributions to open-source ML inference frameworks
• Familiarity with compiler stacks such as MLIR, TVM, or XLA

🎁 Benefits & Perks

• 🏥 Comprehensive health, life, and disability insurance
• 📈 Employee stock ownership
• 💻 Commute subsidy
• ✈️ Generous vacation and personal days
• 👶 Support for new parents through leave and family-care programs

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Screen· 30 min
2. 2Technical Interview· 60 min
3. 3Hiring Manager Interview· 45 min