Perception Engineer

New York Technology Partners; Atlanta (GA); On-site; USD 110,000 - 180,000; Full time

Job summary

New York Technology Partners is seeking a Perception Engineer to develop, optimize, and deploy computer vision and sensing systems for autonomous platforms. This hands-on role spans camera and sensor evaluation, image processing, ML, and embedded software integration with real-time autonomy.

You will translate algorithms into production-ready software, optimizing latency and throughput on edge hardware while collaborating with cross-functional teams to meet system-level requirements.

Qualifications

• Bachelor's or Master's degree in a technical field with robotics or computer vision focus.
• Experience developing computer vision, perception, or sensor-processing systems.
• Proficient in C++ and performance-sensitive software development.
• Understanding of image-processing fundamentals and feature extraction.
• Experience training or evaluating ML models for vision tasks.
• Familiarity with embedded systems and real-time computing.

Responsibilities

• Develop and optimize CV, image-processing, and sensor-processing algorithms for real-time perception.
• Evaluate cameras, lenses, and sensors for resolution, noise, and dynamic range.
• Implement image enhancement, denoising, filtering, feature extraction, and object detection.
• Train and evaluate ML models for detection, classification, tracking, and state estimation.
• Deploy perception software on embedded/edge platforms and optimize latency.
• Collaborate with cross-functional teams to meet system reliability and performance.

Skills

C++

Computer Vision

Embedded Systems

Real-time Computing

Debugging Skills

Data-driven Evaluation

Team Collaboration

Education

Bachelor's or Master's in CS/Engineering

Tools

CUDA

TensorRT

ROS 2

NVIDIA Jetson

Job description

Perception Engineer

About the Role

We are seeking a Perception Engineer to develop, optimize, and deploy computer vision and sensing systems for autonomous platforms. This role spans the full perception pipeline, including camera and sensor evaluation, image processing, machine learning, embedded software deployment, and integration with real-time autonomy systems.

The ideal candidate combines strong software engineering skills with a practical understanding of computer vision, optical sensing, and embedded systems. This is a hands‑on engineering role focused on translating algorithms into reliable, production‑ready systems that perform in real‑world environments.

Responsibilities

• Develop and optimize computer vision, image‑processing, and sensor‑processing algorithms for real‑time perception applications.
• Evaluate cameras, lenses, and image sensors based on resolution, sensitivity, noise, dynamic range, and overall performance requirements.
• Design and implement techniques for image enhancement, denoising, filtering, feature extraction, and object detection.
• Train, fine‑tune, and evaluate machine learning models for object detection, classification, tracking, and state estimation.
• Deploy and optimize perception software on embedded and edge‑computing platforms.
• Improve system performance by optimizing latency, throughput, and computational efficiency using GPU acceleration and related technologies.
• Develop production‑quality C++ software and integrate perception capabilities with robotics and autonomy frameworks.
• Collect, analyze, and evaluate real‑world data to identify performance gaps and improve perception systems.
• Troubleshoot issues across the perception pipeline, including sensor performance, image quality, processing algorithms, and system integration.
• Collaborate with cross‑functional engineering teams to ensure perception outputs meet system‑level performance and reliability requirements.
• Develop testing, benchmarking, and evaluation workflows to measure accuracy, robustness, and real‑time performance.

Basic Qualifications

• Bachelor’s degree in Computer Science, Robotics, Electrical Engineering, Computer Engineering, Aerospace Engineering, or a related technical field, with relevant industry or applied robotics experience; alternatively, a master’s degree in a related discipline.
• Experience developing computer vision, perception, image‑processing, or sensor‑processing systems.
• Proficiency in C++ and experience developing performance‑sensitive software.
• Understanding of image‑processing fundamentals, including filtering, denoising, contrast enhancement, feature extraction, or temporal analysis.
• Experience developing, training, fine‑tuning, or evaluating computer vision or machine learning models.
• Familiarity with embedded systems, real‑time computing, or software deployment under hardware and computational constraints.
• Strong debugging and analytical skills, with an emphasis on data‑driven evaluation and measurable performance improvements.
• Ability to work effectively in a fast‑paced engineering environment and collaborate across multidisciplinary teams.

Preferred Qualifications

• Experience evaluating cameras, lenses, optical systems, or image sensors.
• Familiarity with sensor characteristics, including pixel size, sensitivity, exposure, noise, dynamic range, and resolution.
• Experience deploying computer vision or machine learning applications on embedded platforms such as NVIDIA Jetson.
• Knowledge of CUDA, TensorRT, GPU programming, or performance profiling and optimization.
• Experience with ROS 2 or other robotics middleware.
• Background in sensor fusion, visual‑inertial systems, or multimodal perception involving cameras, radar, or LiDAR.
• Experience with robotics, autonomous systems, unmanned aerial systems (UAS), or field testing.
• Familiarity with dataset development, data labeling, model evaluation metrics, and regression testing.
• Experience transitioning computer vision algorithms from research and prototyping into production‑ready software.