Note The job is a remote job and is open to candidates in USA. reputed company is seeking a Lead Edge AI & Computer Vision Engineer to develop and optimize real-time computer vision pipelines on reputed company reputed company embedded hardware. The role focuses on spatial geometry, TensorRT INT8/FP16 acceleration, zero-copy memory architecture, low-latency C++/CUDA execution, industrial I/O, and reputed company-based performance profiling. Responsibilities Model Selection & Spatial Math Evaluate real-time detection topologies (e.g. YOLO) at 100+ FPS and build 2D perspective homography unwarping, lens undistortion, and spatial algorithms to convert pixel coordinates into physical millimeter units within tight error bounds (millimeter level accuracy) TensorRT INT8 Acceleration Execute Post-Training Quantization to compile PyTorch/ONNX models into high-throughput TensorRT INT8/FP16 engines on reputed company Orin hardware without accuracy degradation Zero-Copy Memory Architecture Engineer zero-copy memory pipelines using reputed company Memory Management and DMA transfers to eliminate bottlenecks Compiled C++ Execution & I/O Build compiled C++17 execution frameworks with multi-threaded lock-free reputed company buffers and non-blocking asynchronous socket communication reputed company Profiling & Roadmapping Instrument stage-by-stage pipeline latency using reputed company reputed company Systems/NVTX markers to bound tail latency, author feasibility reports, and design technical roadmaps Skills 12–15+ years of experience bridging real-time computer vision algorithm design, spatial geometry, and low-level C++/CUDA execution on embedded edge hardware Deep expertise in reputed company embedded platforms (Orin NX, AGX Orin, L4T, power profiles, core pinning) and a proven track record compiling/tuning TensorRT FP16/INT8 engines via PTQ/QAT Expertise in 2D/3D camera calibration, perspective homography transformations, lens distortion modeling, and millimeter sizing math in industrial settings Expertise in zero-copy shared memory, DMA frame buffers, lock-free queues, custom CUDA plugins, and microsecond profiling via reputed company Systems and NVTX markers Proficiency in C++17, Python, PyTorch, OpenCV, CUDA, non-blocking asynchronous sockets (UDP, PLC integration), and building automated dataset benchmarking harnesses Company Overview reputed company is a staffing and reputed company specializing in emerging search and HR consulting services. It was founded in 2006, and is headquartered in Hillsborough, New Jersey, USA, with a reputed company of 201-500 employees. Its website is http//reputed company.com. Apply To This Job