Senior Computer Vision Engineer

Responsibilities

• Design, train, and iterate on custom object detection models for retail environments and inventory tracking
• Fine-tune and deploy open-source vision-language models (LLaVA, Qwen-VL, InternVL, PaliGemma) for product understanding
• Build vision-language-action (VLA) pipelines to translate visual understanding into downstream decisions
• Optimize models for edge deployment using quantization, pruning, and architectural optimization
• Build robust data pipelines and annotation workflows for continuous model improvement
• Mentor engineers and drive technical decisions regarding CV infrastructure

Requirements

• 4+ years of hands-on computer vision engineering with production shipping experience
• Deep expertise with YOLO and YOLO-E architectures
• Hands-on experience fine-tuning and deploying open-source VLMs
• Familiarity with VLA frameworks for real-world perception tasks
• Mastery of edge deployment using TensorRT, ONNX Runtime, or similar frameworks
• Strong software engineering fundamentals including clean code and CI/CD for ML

Preferred Qualifications

• Experience with NVIDIA Jetson products
• Background in retail or inventory management CV applications
• Proficiency with PyTorch and modern training frameworks like Transformers or Unsloth
• Experience with efficient VLM inference using vLLM, llama.cpp, or SGLang
• Knowledge of experiment tracking tools like MLflow or Weights & Biases
• Experience with AWS services including SageMaker and Bedrock

About the Company

Panoptyc is building the future of retail intelligence, developing next-generation computer vision capabilities to power real-world retail applications.