Job Summary
We are looking for a Computer Vision Engineer with hands-on experience in real-time vehicle detection, tracking, and inference pipelines. The role focuses on building low-latency, production-grade perception systems for smart transportation and autonomous applications, with strong emphasis on NVIDIA DeepStream and optimized inference.
Key Responsibilities
- Develop and optimize vehicle object detection models (YOLO, Faster R-CNN, SSD).
- Implement real-time multi-object tracking in dynamic traffic scenarios.
- Build and maintain real-time video analytics pipelines using NVIDIA DeepStream SDK.
- Train, evaluate, and fine-tune models on datasets like KITTI, COCO, and custom data.
- Optimize inference using TensorRT / ONNX for edge and GPU deployments.
- Deploy and integrate models on NVIDIA Jetson and cloud platforms.
- Collaborate with software and hardware teams; document architectures and benchmarks.
Qualifications
- Bachelor's or Master's degree in CS, EE, AI, or related field.
- Strong proficiency in Python and C++.
- Experience with PyTorch or TensorFlow.
- Solid understanding of CNN-based vehicle detection and tracking systems.
- Hands-on experience with DeepStream, TensorRT, and real-time video pipelines.
- Familiarity with GPU acceleration, Git, and CI/CD workflows.
Preferred
- Embedded / edge AI experience (automotive, defense, IoT).
- Knowledge of ROS, CAN, or sensor fusion (camera + LiDAR/radar).
What We Offer
- Competitive salary and benefits.
- Hybrid work flexibility.
- Opportunity to work on high-impact, real-world computer vision systems.
