We are a fast-growing technology company building advanced AI and real-time Computer Vision platforms.

We currently develop multiple parallel systems, including:

• Real-time video analytics platforms (object detection, tracking, anomaly recognition)
• Edge AI platforms running on NVIDIA Jetson
• AI-powered automation and analytics platforms

• Data extraction & document intelligence platforms (OCR, VLMs, pipelines)

We are expanding our engineering team and looking for a Computer Vision Engineer capable of building production-grade pipelines from model training to deployment.

Responsibilities

• Develop and optimize real-time object detection & tracking pipelines
• Train and fine-tune DL models (YOLO, Detectron2, segmentation networks)
• Optimize inference with TensorRT, ONNX, pruning, quantization
• Work with RTSP/CCTV video streams and drone/edge camera inputs
• Deploy models on NVIDIA Jetson (Orin/Xavier) and GPU servers
• Integrate CV modules into backend services (FastAPI, Docker, messaging queues)
• Collaborate with ML/AI/backend teams on architecture and performance

Requirements

• Strong Python and OpenCV skills
• Experience with PyTorch or TensorFlow
• Hands-on experience with object detection / segmentation / tracking
• Understanding of real-time inference and latency optimization
• Experience with TensorRT / ONNX / Jetson is a strong plus
• Knowledge of SLAM / VIO / sensor fusion is an advantage (not mandatory)
• Experience with datasets, augmentation, and model training workflows

What We Offer

• Work on impactful AI & CV platforms used in real-world environments
• Opportunity to contribute to real-time, edge-based, and automation systems
• Flexible schedule (full-time preferred)
• Fast engineering culture

• Competitive compensation based on experience and project fit

How to Apply

Send your Djinni profile or CV, we review applications manually and will reach out for a short intro call if there’s a match.