R

Senior Perception Software Engineer

Rethink recruit
Full-time
On-site
San Francisco, California, United States
Software / Technology / IT
Sauron is redefining home security through a fusion of cutting-edge technology and elite human oversight. Founded in 2024 by Kevin Hartz, Jack Abraham, and Vasu Raman, the company offers an autonomous security platform that combines AI-driven 3D perception, LiDAR, facial recognition, and thermal imaging to deliver real-time, 360° situational awareness . Sauron's IRIS Command Center, staffed 24/7 by professionals from law enforcement and military backgrounds, ensures immediate and precise threat response . With features like predictive threat modeling and seamless user interfaces, Sauron not only detects but actively deters potential intrusions, setting a new standard in residential security .
 
This role involves model design, development, and evaluation for perception tasks that include both classic computer vision approaches and more modern ML approaches. Our hardware will operate around the home and must be able to complete its mission reliably in the face of all environmental conditions. We aim to build a system that handles a wide variety of scenarios and do so without error. This role will be highly collaborative with our hardware team to develop requirements needed for sensing, tracking, and other perception tasks, as well as iteration for various generations of hardware.

 

We Value

  • Collaboration, pair programming, and teamwork.

  • Making small improvements and shipping code to production continuously.

  • Taking ownership across the stack.

  • Test-driven development, and refactoring regularly to keep our codebases healthy.

 

You Will Contribute By

  • Extracting the maximum value from our sensors, fusing all observations available while being robust to occlusions, poor lighting and disguises

  • Assisting in the collection, labeling, and management of datasets to train and evaluate ML models.

  • Leveraging state of the art models for 3D object detection, tracking, facial recognition and semantic scene understanding, and push them to the limits of their performance in this problem domain.

  • Analyzing the performance of systems both in simulation and using data from deployments in the field to find headroom and devise solutions to reduce it.

  • Probing the inner workings of neural networks to uncover and mitigate edge case failures.

  • Contributing to machine learning infrastructure (e.g. distributed training, continuous model integration, data management, and evaluation of production systems).

 

Your Background Includes

  • 4+ years of professional experience with machine learning for hardware products in a safety-critical field, e.g. aerospace, robotics, medical devices, autonomous vehicles.

  • Passionate about ML, both robust engineering and research challenges.

  • An understanding of the theory and practice of modern machine learning techniques.

  • A clear grasp of basic linear algebra, optimization, statistics, and algorithms.

  • Experienced at facets of training and using deep-learning models, including writing custom layers/operations, optimizing networks for inference on edge compute, reproducibility and evaluation.

  • Experience working with PytorchTensorflow or other modern deep learning frameworks.

  • Familiar with the use of VLMs and other multi-modal models for semantic scene understanding and description.

  • Able to solve complex problems with little supervision.

  • Excellent communicator, both written and verbal.

  • A generalist mindset and can dive in wherever the bottlenecks are, whether that be spooling up cloud compute services to optimizing for embedded systems.

 

Nice to Have

  • Experience building high-performance software systems using compiled languages (C/C++/Rust/etc.).

  • Experience with Middleware frameworks such as ROS.

  • Experience with build systems such as Bazel, CMake.

  • Experience in GPU architecture and CUDA programming.