Top Skills:
Computer Vision (Detection, Segmentation, Classification, OCR)
Python
PyTorch and/or TensorFlow
Machine Learning Model Development & Optimization
Image & Video Analysis
Taking Models from Prototype to Production
Job Description:
What You Will Be Doing:
Applied Model Development: Own the end-to-end development of computer vision and ML models-covering detection, segmentation, classification, OCR and image/video analysis.
Model Evaluation & Selection: Evaluate model options, benchmark trade-offs, and recommend the right approach for each business problem.
Training & Fine-Tuning: Train, fine-tune, and optimize models using PyTorch or TensorFlow, including transfer learning and data-efficient techniques.
Performance Analysis: Define metrics, analyze model performance, diagnose failure modes, and iterate to meet accuracy and latency targets.
Hardware-Aware Engineering: Account for the real-world constraints of cameras, sensors, lighting, and edge devices that affect data quality and model performance.
Data Pipelines: Build and maintain data, labeling, and evaluation pipelines that support reliable experimentation and deployment.
Collaboration: Work with software, hardware, and MLOps engineers to take models from prototype to production.
Qualifications
Qualifications we are looking for.
Experience:
3-5 years of hands-on experience building computer vision and machine learning models.
Proven track record taking models from experimentation to production.
Skills:
Proficiency in both modern AI-based CV models (CNNs, transformers, embeddings) and traditional computer vision
Strong Python skills for CV/ML development, data processing, and experimentation.
Experience with PyTorch or TensorFlow.
Hands-on experience with detection, segmentation, classification, and image/video analysis.
Practical knowledge of computer vision hardware-cameras, sensors, lighting, and edge devices-and the real-world constraints that affect data quality and model performance.
Experience with broader ML problems: time-series modeling, anomaly detection, clustering, and data analysis.
Abilities:
Strong analytical and performance-debugging skills.
Able to evaluate model options and turn business problems into practical AI solutions.
Strong problem-solving skills and ability to work in a fast-paced, agile environment.
Education:
Bachelor's or Master's degree in Computer Science, Engineering or a related field.
Preferred Qualifications:
Experience deploying models to edge devices or optimizing for inference (quantization, pruning, TensorRT, ONNX).
Familiarity with MLOps practices: experiment tracking, model versioning, and drift/performance monitoring.
Experience with cloud platforms (Azure, AWS, or GCP) and GPU-based training.
Experience working with retail, IoT, or real-world imaging datasets.