Real-time AI Vision Engineer: LPR/OCR & Edge Inference

Fullstack Labs, Inc.; Ciudad de Mendoza; Remote; ARS 1,000,000 - 1,600,000; Full time

Job summary

Fullstack Labs, Inc. is seeking an experienced computer vision/ML engineer to build production AI vision systems. You will design, train, and deploy models for object detection, attribute extraction, and OCR from real-time image and video streams.

You will implement low‑latency inference across cloud and edge devices, and architect robust pipelines for high‑throughput processing, including LPR/OCR and multi‑object tracking capabilities.

Qualifications

• 3+ years of hands-on experience designing and deploying CV and DL models in production.
• Deep expertise with modern object detection architectures (YOLO, DETR, Faster R‑CNN, ViTs).
• Strong Python skills and experience with PyTorch, OpenCV, and TensorFlow.
• Experience with video stream ingestion, frame processing, and low-latency inference.
• Experience with LPR/OCR and attribute inference systems.

Responsibilities

• Design, train, and fine‑tune state‑of‑the‑art vision models for production.
• Architect, develop, and maintain streaming pipelines for high‑throughput video/text data.
• Implement low‑latency inference on cloud and edge devices using TensorRT/ONNX.
• Curate datasets, annotations, and automated retraining/evaluation loops.

Skills

Vision model deployment

YOLO/DETR/ViT

Python programming

PyTorch/OpenCV/TF

Video stream processing

Low-latency inference

LPR/OCR

Model quantization/ONNX/TensorRT

Tools

PyTorch

OpenCV

TensorFlow

Job description

Fullstack Labs, Inc. is seeking an experienced computer vision/ML engineer to build production AI vision systems. You will design, train, and deploy models for object detection, attribute extraction, and OCR from real-time image and video streams.

You will implement low‑latency inference across cloud and edge devices, and architect robust pipelines for high‑throughput processing, including LPR/OCR and multi‑object tracking capabilities.