Tech Stack

Description

You will design, optimize, and deploy computer vision and multimodal ML models on constrained edge platforms for in-vehicle camera systems, applying techniques like quantization and pruning to achieve real-time inference. Collaborate with cross-functional teams to productize ML runtime pipeline and drive best practices in model optimization and deployment.

Requirements

• 5+ years experience developing and deploying deep learning models for edge/embedded systems.
• Strong background in computer vision.
• Experience with model optimization for real-time inference.
• Ability to mentor and collaborate cross-functionally.
• Experience deploying ML models in production.

Responsibilities

• Design, optimize, and deploy computer vision and multimodal ML models on edge platforms.
• Apply model optimization techniques such as quantization, pruning, and distillation.
• Partner with ML research and product teams to translate AI detections into deployable edge models.
• Collaborate with firmware, ML research, and hardware teams to productize ML runtime pipeline.
• Develop performance benchmarking and validation frameworks for edge-deployed models.