Summary
✨ AI‑Generated
An AI-focused engineering team is seeking a Computer Vision and AI/ML Engineer to build real-time systems for detection, classification, tracking, and behavior analysis. You will work with image and video datasets, develop deep-learning models, explore vision-language capabilities, deploy models to edge devices, and expose AI functionality through production APIs.
Highlights
Develop real-time computer vision and AI/ML systems for challenging visual intelligence problems. The role spans the full ML lifecycle from data preparation and training through evaluation and edge deployment, with opportunities to work on vision-language models and low-latency AI.
Description
- Design and implement Computer Vision and AI/ML models for people and vehicle detection, classification, tracking, and behavior analysis.
- Develop and optimize real-time object detection and recognition systems using deep learning techniques and modern computer vision frameworks.
- Work with image and video datasets from surveillance and edge devices, including data preparation, annotation, training, validation, and performance evaluation.
- Apply object detection, motion tracking, image classification, and pattern recognition techniques to solve real-world computer vision problems.
- Develop and integrate Vision-Language Models (VLMs) for visual understanding, image analysis, and intelligent AI applications.
- Deploy and optimize computer vision models on edge devices, focusing on low-latency inference, resource efficiency, and real-time performance.
- Build and integrate REST APIs to expose AI/Computer Vision models and connect them with production applications and backend systems.
- Collaborate with product and engineering teams to integrate AI models and computer vision pipelines into production environments.
- Continuously improve model performance through dataset refinement, augmentation, fine-tuning, and feature engineering.
- Conduct detailed error analysis to identify false positives and false negatives and implement advanced filtering and post-processing techniques.
- Monitor and optimize model performance across different environments, cameras, lighting conditions, and deployment hardware.
- Translate complex AI and computer vision results into clear insights, metrics, and visualizations for technical and non-technical stakeholders.
- Stay up to date with state-of-the-art research in computer vision, deep learning, VLMs, and edge AI and evaluate their applicability to production use cases.
