Perception Engineer

Job Title: Perception Engineer

Location: Bangalore

Job Type: Full-time

About the Role:

We are seeking a Perception Engineer to develop and optimize cutting-edge computer vision and deep learning models for real-time applications on edge devices. The ideal candidate will have experience in deep learning, ground truthing, object detection, and model training for resource-constrained environments. You will work closely with a multidisciplinary team to enhance the perception stack for autonomous systems, ADAS, robotics, and other intelligent applications.

Key Responsibilities:

• Design, develop, and optimize deep learning models for object detection, lane segmentation, and classification in real-time applications.
• Implement ground truthing pipelines, ensuring high-quality labeled datasets for training and validation.
• Train and fine-tune deep learning models using datasets curated from various sources, including cameras, LiDAR, and radar.
• Deploy and optimize perception models on edge computing platforms (e.g., NVIDIA Jetson, Qualcomm Snapdragon, Intel Movidius).
• Develop data preprocessing, augmentation, and model evaluation strategies to improve performance and accuracy.
• Collaborate with hardware and software teams to integrate perception models into embedded systems.
• Conduct experiments and benchmarking to assess the efficiency of models in real-world scenarios.
• Stay up to date with advancements in computer vision, deep learning, and edge AI.

Qualifications & Skills:

• Bachelor's, Master's, or Ph.D. in Computer Science, Electrical Engineering, Robotics, or a related field.
• Strong expertise in deep learning frameworks such as TensorFlow, PyTorch, ONNX, or OpenVINO.
• Hands-on experience in object detection architectures (e.g., YOLO, Faster R-CNN, SSD, EfficientDet).
• Experience with ground truthing tools and dataset management for supervised learning.
• Proficiency in Python and C++, with experience in OpenCV, NumPy, and TensorRT for optimization.
• Experience deploying models on edge devices and working with hardware accelerators (e.g., GPU, TPU, NPU).
• Knowledge of sensor fusion techniques, including camera-LiDAR fusion, is a plus.
• Familiarity with MLOps, model quantization, pruning, and compression techniques for edge deployment.
• Strong problem-solving skills, ability to work in a fast-paced environment, and passion for innovation.

Preferred Experience:

• Experience in ADAS, robotics, autonomous systems, or industrial automation.
• Hands-on experience with ROS/ROS2 for real-time robotic perception.
• Knowledge of embedded systems, FPGA, or real-time operating systems (RTOS).