Real-time Vision Engineer: LPR/OCR & Low-Latency Inference

Perle Systems; Ciudad de Mendoza; On-site; ARS 1,800,000 - 3,000,000; Full time

Job summary

Perle Systems in Mendoza is seeking an experienced Computer Vision Engineer to design and deploy production AI vision systems for real-time attribute extraction from image and video streams. You will work on state-of-the-art models and build low-latency processing pipelines to support high-throughput video streams.

You will train and fine-tune detectors such as YOLO, DETR, and ViT, implement LPR/OCR and MOT, and optimize performance on cloud and edge devices using TensorRT, ONNX, and OpenVINO.

Qualifications

• 3+ years of hands-on experience in production CV and deep learning systems.
• Deep expertise with modern object detection architectures (YOLO, DETR, Faster R-CNN, ViT).
• Strong programming in Python and DL frameworks (PyTorch, OpenCV, TensorFlow).
• Experience with video stream ingestion, frame processing, and low-latency inference.
• Experience with LPR, OCR, or fine-grained attribute inference systems.
• Familiarity with model quantization, ONNX export, and TensorRT compilation.

Responsibilities

• Research and architect production AI vision systems for real-time attribute extraction from image/video streams.
• Train and fine-tune state-of-the-art vision models (YOLO, DETR, transformers) for object detection and attribute extraction.
• Build low-latency pipelines for ingestion and processing of high-throughput video and image streams.
• Develop plate recognition (LPR/ANPR), OCR, and multi-object tracking capabilities.
• Optimize model performance on cloud (Kubernetes/GCP) and edge devices using TensorRT, ONNX, OpenVINO.
• Curate and augment datasets; establish automated retraining loops and evaluation frameworks.

Skills

Python programming

PyTorch

OpenCV

TensorFlow

Video processing

Low-latency inference

Tools

YOLO

DETR

Faster R-CNN

Vision Transformers

TensorRT

ONNX

OpenVINO

GCP

Kubernetes

Job description

Perle Systems in Mendoza is seeking an experienced Computer Vision Engineer to design and deploy production AI vision systems for real-time attribute extraction from image and video streams. You will work on state-of-the-art models and build low-latency processing pipelines to support high-throughput video streams.

You will train and fine-tune detectors such as YOLO, DETR, and ViT, implement LPR/OCR and MOT, and optimize performance on cloud and edge devices using TensorRT, ONNX, and OpenVINO.