Requirements

• Bachelor's degree or equivalent practical experience.
• 8 years of experience in C++ or Python, modern machine learning frameworks (e.g., JAX, PyTorch), and on-device/cloud inference runtimes.
• Experience optimizing latency, bandwidth, reliability, compute, memory, energy, and cost constraints across device, mobile, and cloud layers.
• Experience with asynchronous architectures, streaming data, state management, buffering, backpressure, fault tolerance, observability, and production debugging.

Nice to Haves

• PhD in Distributed Systems for advanced Machine Learning or Embedded Systems.

What You'll Be Doing

• Architect, design, and build distributed, asynchronous AI systems spanning wearable smart glasses, mobile devices, and cloud infrastructure, managing real-time multimodal streaming, state management, buffering, backpressure, and fault tolerance.
• Lead integration of computer vision, language, and multimodal models into production systems, including design of routing and decision-making mechanisms based on model uncertainty and confidence calibration.
• Drive system-wide performance and reliability across device, mobile, and cloud boundaries managing trade-offs involving latency, bandwidth, compute, memory, battery life, thermal limits, and inference cost.
• Collaborate with machine learning researchers and hardware teams to co-design constrained edge and mobile inference pipelines using quantization, model compression, hardware acceleration, and scalable cloud AI serving.
• Establish evaluation frameworks, production observability, and debugging tools to measure and improve end-to-end system performance and user experience.