Senior ML/AI Engineer (Computer Vision & Image Processing)

AI71 is an applied research team dedicated to advancing cloud-based AI solutions for knowledge workers. Partnering closely with industry leaders, our cross-functional teams of AI experts deliver innovative products based on cutting-edge research at the Technology Innovation Institute (TII). We are seeking an AI/ML Engineer with expertise in computer vision and image processing.

The ideal candidate will develop and optimize deep learning models and vision-language models (VLMs) for:

• Object detection
• Segmentation
• Classification
• Text extraction
• Fine-tuning for domain-specific applications

Key Responsibilities:

1. Develop & Deploy AI Models

   • Train and optimize models for architectural drawings (object detection, segmentation, and classification).
   • Fine-tune YOLO, R-CNN, and transformer-based models to improve accuracy and efficiency for domain-specific tasks.
   • Implement OCR and symbol recognition for automated compliance checking.

2. Image Processing & Enhancement

   • Develop lossless image compression and feature extraction techniques.
   • Improve image pre-processing pipelines for architectural data quality.
   • Utilize OpenCV and Deep Learning for drawing analysis.

3. Fine-Tuning & Model Adaptation

   • Customize and fine-tune pre-trained VLMs to enhance multimodal AI capabilities.
   • Optimize models, embeddings, and transfer learning strategies based on real-world feedback and evolving datasets.

4. AI Model Optimization & Deployment

   • Optimize model architectures to reduce computational costs while maintaining accuracy.
   • Deploy AI models on cloud or on-prem infrastructure; experience with Docker/Kubernetes is a plus.
   • Integrate AI workflows into AutoCAD and BIM environments is a plus.

Key Skills & Technical Expertise:

• Computer Vision & Deep Learning: OpenCV, YOLO, R-CNN, Mask R-CNN, EfficientNet
• OCR & Symbol Extraction: Tesseract, EasyOCR, NLP for document parsing
• Fine-Tuning & Transfer Learning: VLMs, CLIP, Transformer-based architectures
• Programming: Python, C++
• Cloud & Deployment: AWS, Azure, GCP, TensorFlow Serving, ONNX
• Image Processing: Feature extraction, noise reduction, compression techniques

General Skills & Competencies:

• 5+ years of experience in computer vision solutions.
• Strong problem-solving skills in computer vision applications.
• Ability to optimize AI pipelines for real-world datasets.
• Experience integrating AI models into software applications.
• Familiarity with CAD tools (AutoCAD, Revit, DXF/DWF processing) is a plus.