Machine Learning Systems Engineer, Video Computer Vision

What you'll do

• Develop on-device software that integrates multimodal AI models and computer vision technologies into production systems.
• Optimize inference latency, memory footprint, and computational efficiency of CV/ML models for mobile devices.
• Benchmark and profile the power consumption and thermal performance of models running on Apple silicon.
• Design experiments to evaluate quality versus on-device deployment tradeoffs for system design decisions.
• Debug concurrent systems on embedded devices using existing tools or by developing new debugging visualizations.
• Implement Supervised Fine-Tuning (SFT) pipelines to adapt foundation models for specific on-device tasks.
• Optimize machine learning models specifically for neural network accelerators and mobile GPUs.

What we're looking for

• Bachelor's degree in Computer Science, Machine Learning, or a related discipline.
• 3+ years of relevant industry experience.
• Strong machine learning fundamentals and knowledge of multimodal LLM architectures.
• Proven track record of writing production code for on-device CV/ML features on embedded platforms.
• Extensive programming experience in Python and C++.
• Solid understanding of operating system fundamentals.
• Hands-on experience with PyTorch and the end-to-end ML lifecycle including data preprocessing, training, and edge deployment.
• Experience with Supervised Fine-Tuning (SFT) pipelines for vision and multimodal foundation models.