Machine Learning Systems Engineer, Video Computer Vision

What you'll do

• Develop on-device software to bridge multimodal AI models and computer vision technologies with production systems.
• Optimize inference latency, memory footprint, and computational efficiency of CV/ML models for on-device deployment.
• Benchmark and profile the power consumption and thermal performance of models running on Apple silicon.
• Design experiments and evaluations to analyze quality and on-device deployment tradeoffs for system design decisions.
• Debug concurrent systems on embedded devices and develop innovative debug tools and visualizations.
• Participate in post-training model alignment and evaluation in partnership with algorithm researchers.
• Build software infrastructure to deliver multimodal context to models and optimize the software harness.

What we're looking for

• Bachelor’s degree in Computer Science, Machine Learning, or a related discipline.
• 3+ years of relevant industry experience.
• Strong ML fundamentals and a robust understanding of machine learning architectures, specifically Multimodal LLMs.
• Proven track record of writing high-quality production code for shipped on-device CV/ML features on embedded platforms.
• Extensive programming experience in Python and C++ with a solid understanding of operating system fundamentals.
• Hands-on experience with PyTorch and the end-to-end ML lifecycle, including data preprocessing, training, evaluation, and edge deployment.
• Experience with Supervised Fine-Tuning (SFT) pipelines to adapt vision and multimodal foundation models for on-device tasks.
• Programming experience with Swift and familiarity with CoreML, CoreFoundation, and RealityKit frameworks (preferred).