Computer Vision Engineer (4 yrs+)

Job Description:

• Strong programming skills in Python for AI/ML development.

• Strong programming skills in C++ for performance-critical image processing and deployment.

Experience with:

• Object detection model training (YOLO, Detectron2, MMDetection, etc.)

• Computer vision using OpenCV

• Video processing and frame extraction

• Dataset preparation, annotation, and evaluation

• PyTorch or equivalent deep learning frameworks

• Linux development environment

Preferred Skills

• Experience with Rust for high-performance and memory-safe applications.

• Experience with synthetic data generation and image augmentation.

• Experience with Vision Language Models (VLMs) such as CLIP, LLaVA, Florence, Grounding DINO, OWL-ViT, or GPT-based vision models.

• Experience with retail shelf analysis, product recognition, or SKU detection.

• Knowledge of GPU optimization, CUDA, TensorRT, ONNX Runtime.

• Experience deploying models to edge devices, servers, or mobile platforms