Real-Time AI Vision Systems Engineer

Somniosoftware; Ciudad de Mendoza; On-site; ARS 1,800,000 - 2,400,000; Full time

Job summary

Somniosoftware seeks a Senior Computer Vision Engineer to design and deploy production-grade AI vision systems that operate on real-time image and video streams. You will architect detection models, train on diverse datasets, and build high-throughput, low-latency pipelines for cloud and edge environments.

You will work with YOLO variants, DETR, and Vision Transformers, optimizing models with TensorRT/ONNX and validating performance on streaming data sources.

Qualifications

• 3+ years hands-on experience designing and deploying computer vision models in production.
• Deep expertise with modern object detection architectures (YOLO, DETR, Faster R-CNN, Vision Transformers).
• Strong programming skills in Python and deep learning frameworks (PyTorch, OpenCV, TensorFlow).
• Proven 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 for hardware acceleration.

Responsibilities

• Research, architect, and build production AI vision systems for real-time attribute extraction from image and video streams.
• Design and fine-tune state-of-the-art vision models (YOLO variants, DETR, Transformers).
• Develop low-latency streaming pipelines (RTSP, WebRTC) for high-throughput data.
• Implement LPR/OCR and multi-object tracking components and optimize for cloud and edge deployment.
• Experiment with quantization, ONNX export, and TensorRT for hardware acceleration.

Tools

Python

PyTorch

OpenCV

TensorFlow

YOLO

DETR

Faster R-CNN

Vision Transformers

TensorRT

ONNX

Job description

Somniosoftware seeks a Senior Computer Vision Engineer to design and deploy production-grade AI vision systems that operate on real-time image and video streams. You will architect detection models, train on diverse datasets, and build high-throughput, low-latency pipelines for cloud and edge environments.

You will work with YOLO variants, DETR, and Vision Transformers, optimizing models with TensorRT/ONNX and validating performance on streaming data sources.