Senior 3D Perception Engineer – Autonomous Security (On-site, Equity)

Knightscope; Sunnyvale (CA); On-site; USD 240,000 - 275,000; Full time

Benefits offered by this job

Medical

Dental

Vision

401(k)

Paid time off

Job summary

Knightscope seeks a senior ML/Robotics engineer to own the full perception stack for its autonomous security robot platform. You will design and deploy 3D perception from LiDAR, camera, and thermal data, enabling real-time threat detection and evidence capture on edge hardware.

You will lead cross-functional teams, optimize models for production with TensorRT/CUDA, and advance integration of Vision-Language capabilities for richer scene descriptions. On-site in Sunnyvale, CA with no relocation.

Qualifications

• 7+ years hands-on experience at an OEM, AV company, physical security platform, or robotics tech company shipping perception software to production.
• Deep expertise in 3D computer vision: LiDAR/camera 3D object detection, point cloud processing, multi-view geometry, and sensor fusion.
• Strong ML fundamentals, CNNs, Transformers, multi-task architectures, with production deployment experience (TensorRT, ONNX, CUDA optimization).
• Fluency in C++ (real-time systems) and Python; experience with ROS2 and simulation environments (CARLA, Isaac).
• Production-first mindset demonstrated ability to take models from research to deployed, real-world systems operating under real operational constraints.

Responsibilities

• Design, train, and deploy 3D perception models using multi-modal sensor data (LiDAR, camera, thermal).
• Own end-to-end ML pipeline from data curation to model training and onboard deployment on edge compute.
• Build persistent cross-sensor identity across camera handoffs and time for incident generation.
• Design and implement evidence-first capture with replay-safe media and outputs for analysts.
• Explore Vision-Language Models to enrich detection outputs with scene narration and anomaly reasoning.
• Drive architecture and data strategy; mentor engineers across the team.
• Conduct offline and closed-loop evaluations; define metrics for safety-critical perception performance.

Skills

3D computer vision

LiDAR/camera fusion

C++

Python

ROS2

TensorRT/ONNX/CUDA

Education

MS or PhD in Computer Science, Robotics, or Electrical Engineering

Tools

CARLA

Isaac

ROS2

TensorRT

ONNX

CUDA

Job description

Knightscope seeks a senior ML/Robotics engineer to own the full perception stack for its autonomous security robot platform. You will design and deploy 3D perception from LiDAR, camera, and thermal data, enabling real-time threat detection and evidence capture on edge hardware.

You will lead cross-functional teams, optimize models for production with TensorRT/CUDA, and advance integration of Vision-Language capabilities for richer scene descriptions. On-site in Sunnyvale, CA with no relocation.