You will be joining a world-class team of RF, Hardware, Software, SaaS, and Cloud developers in an exciting new early-stage startup that will revolutionize the contentious and dangerous physical security procedure of a “pat-down” with a safe from distance and more accurate virtual
search. You will have significant leeway in your design project and will be able to make a huge impact on the company, business, and market.

We are looking for an initiative-taking self-starter who is passionate about developing great product designs and about the space we are in. The position is in the Los Gatos, CA area and some travel to our Bellevue, WA office will be required. This position carries with it a very competitive salary, benefits, and equity package in an extremely exciting early-stage startup.

Key Responsibilities:

• Design, develop, and deploy deep learning models for computer vision applications.
• Optimize and quantize models to run efficiently on embedded devices, specifically Xilinx
  platforms.
• Collaborate with hardware engineers to integrate AI solutions into embedded systems.
• Develop and maintain efficient workflows for deploying PyTorch-based models on edge
  devices.
• Research and implement state-of-the-art deep learning techniques for computer vision
  tasks such as object detection, segmentation, and classification.
• Debug and troubleshoot deployment issues on embedded hardware.
• Collaborate with cross-functional teams to define requirements and deliver robust
  solutions.

Requirements:

• Bachelor’s, Master’s, or Ph.D. in Computer Science, Electrical Engineering, or a related
  field.
• Proven experience in deploying deep learning models on embedded devices like Xilinx,
  NVIDIA Jetson, or similar.
• Familiarity with deployment challenges, such as latency optimization and memory
  constraints on edge devices.
• Strong expertise in computer vision and deep learning algorithms.
• Proficient in PyTorch with hands-on experience in model training, optimization, and
  quantization.
• Familiarity with tools and frameworks for model deployment, such as TensorRT, ONNX,
  or Vitis AI.
• Strong understanding of embedded systems, resource constraints, and low-power
  optimization.
• Knowledge of hardware accelerators (e.g., FPGAs, GPUs) and their integration with AI
  workflows.
• Solid programming skills in Python.
• Ability to work collaboratively in a fast-paced, multidisciplinary environment.

Preferred Qualifications:

• Experience with Xilinx Vitis AI or similar FPGA tools.
• Experience in hardware-aware model design and pruning techniques.