Senior Machine Learning Engineer - Edge AI

Samsara Samsara · Enterprise · San Francisco, CA · Remote · Safety

Senior Machine Learning Engineer focused on Edge AI for in-vehicle camera systems. The role involves designing, optimizing, and deploying computer vision and multimodal ML models on constrained edge platforms, applying techniques like quantization and pruning for real-time inference. Responsibilities include collaborating with research and firmware teams, developing performance frameworks, and improving the edge ML toolchain. Requires 5+ years of experience in edge ML deployment, computer vision/multimodal ML, Python/C++, and performance tuning on constrained hardware.

What you'd actually do

  1. Design, optimize, and deploy computer vision and multimodal ML models that run efficiently on constrained edge platforms powering Samsara’s in-vehicle camera systems.
  2. Apply advanced model optimization techniques—such as quantization, pruning, and distillation—to achieve real-time inference under strict CPU, memory, and thermal constraints.
  3. Partner with ML research and product teams to translate new AI detections into deployable, maintainable edge models.
  4. Collaborate with firmware, ML research, and hardware teams to productize our ML runtime pipeline, bringing scalable, reliable, and testable on-device inference to production.
  5. Develop performance benchmarking, profiling, and validation frameworks for edge-deployed models to ensure robustness across millions of deployed devices.

Skills

Required

  • 5+ years of experience developing and deploying deep learning models for edge, embedded, or real-time systems.
  • Strong background in computer vision or multimodal ML (e.g., 2D/3D CNNs, Transformers) using industry-standard deep learning frameworks.
  • Proficiency in Python and C++
  • hands-on experience optimizing inference runtimes
  • applying model optimization techniques for edge deployment
  • Deep understanding of performance tuning, including compiler- or DSP-level optimizations, runtime profiling, latency analysis, and memory management on constrained hardware.
  • Familiarity with middleware or streaming frameworks used in real-time perception pipelines.
  • Excellent cross-functional communication and collaboration skills, especially across ML, firmware, and product domains.

Nice to have

  • Experience bringing ML infrastructure or runtime systems from prototype to production at scale.
  • Background in multimodal ML (e.g., audio + vision fusion) or event-based detection systems.
  • Experience validating AI models across large, diverse fleets of deployed devices in real-world environments.

What the JD emphasized

  • developing and deploying deep learning models for edge, embedded, or real-time systems
  • optimizing inference runtimes
  • applying model optimization techniques for edge deployment
  • performance tuning
  • latency analysis
  • memory management on constrained hardware

Other signals

  • deploying efficient, reliable, and scalable AI models
  • highly constrained embedded environments
  • real-time inference
  • model optimization techniques