Drimva

Sauron

Senior Perception Engineer

San Francisco, United States · On-site · Senior · Full-time · Posted Sep 29, 2026

Experience
Around 5+ years building production systems, with several at staff scope.

About the job

Own the architecture, technical direction, and end-to-end quality of a home-security perception system that interprets sensor data reliably across challenging conditions.

What you'll do

  • Evolve the perception pipeline to support changing cameras and configurations without interrupting video or losing object identity.
  • Define and measure perception quality, including evaluation data, regression testing, model selection, and performance tradeoffs.
  • Improve reliability in field deployments through sensor fusion, failure detection, graceful degradation, observability, and deployment-data feedback.

What they ask for

  • Significant professional experience in perception or machine learning for hardware products in a safety-critical field.
  • Deep modern C++ experience; the codebase uses C++20, Abseil, gRPC, and CMake.
  • Real GStreamer or media-pipeline experience and shipped applied computer vision, such as multi-object tracking, re-identification, or multi-camera association.
  • Experience across the deep-learning lifecycle and practical GPU inference; Python fluency.

Nice to have

  • NVIDIA Jetson production experience or experience building multi-camera tracking systems.
  • Video surveillance, VMS, or ONVIF/RTSP integrations; GPU architecture and CUDA; familiarity with VLMs or other multimodal models.

Tools

C++20, Abseil, gRPC, CMake, GStreamer, PyTorch, TensorRT, Python

AI focus

Develop and evaluate computer-vision and machine-learning perception for sensor fusion, object tracking, re-identification, and semantic scene understanding; optimize models for edge inference.

Model-written summary · the original posting is authoritative

First seen Oct 29, 2026 · Last verified Nov 5, 2026 (UTC)