🛠 Tech Stack

💼 About This Role

You'll bring modern ML capabilities directly onto consumer hardware, focusing on fast, private, and reliable local AI. You'll own the design and optimization of models running on iPhone/iPad/Mac-class devices, with an emphasis on latency, battery, and real-world UX. This role sits at the intersection of ML systems, product engineering, and performance tuning.

🎯 What You'll Do

• Convert, optimize, and deploy models using Core ML and/or MLX
• Build and optimize local retrieval pipelines for offline RAG
• Own the on-device model lifecycle including updates and rollbacks
• Profile and improve model execution across CPU/GPU/Neural Engine

📋 Requirements

• Experience shipping ML features into production on mobile/edge devices
• Hands-on proficiency with Core ML and/or MLX
• Solid understanding of quantization and optimization for inference
• Fluency in performance engineering on real devices

✨ Nice to Have

• Experience with on-device LLMs or multimodal models
• Familiarity with Metal/GPU compute on Apple platforms
• Experience designing privacy-preserving personalization and memory

🎁 Benefits & Perks

• 💰 Competitive salary and performance-based incentives
• 🏥 Comprehensive health, dental, vision
• 🏖️ Unlimited Approved PTO
• 📚 $400/year Continuing Education Credit
• 🏋️ $200/mo Health and Wellness Stipend

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Screen· 30 min
2. 2Technical Interview· 60 min
3. 3On-site or Virtual Loop· 180 min