Job Title: ML Engineering
Key ResponsibilitiesLead the design, development, and deployment of fruit defect detection models using object detection and image segmentation techniques.
Build and optimize deep learning pipelines using frameworks like PyTorch or TensorFlow.
Collaborate with domain experts to define and classify defect categories and edge cases (e.g., bruises, rot, discoloration, deformities).
Develop and manage data pipelines, including dataset curation, labeling workflows, and data augmentation strategies.
Ensure model performance and scalability across varied lighting and environmental conditions.
Work with product and engineering teams to deploy models into production (cloud or edge environments).
Research and integrate state-of-the-art computer vision models (e.g., YOLOv8, EfficientDet, Mask R-CNN, Vision Transformers, DETR).
Mentor and guide junior ML engineers and research interns.
Build evaluation dashboards and explainability tools for QA and business teams to monitor model health.
7+ years of experience in AI/ML, with at least 4+ years focused on Computer Vision.
Strong expertise in object detection, image segmentation, and classification techniques.
Hands-on experience with PyTorch and/or TensorFlow.
Deep understanding of CNNs, transfer learning, and model optimization.
Proficiency in Python and libraries like OpenCV and NumPy.
Proven ability to handle real-world noisy datasets and perform data preprocessing effectively.
Experience in model deployment using ONNX, TensorRT, or REST APIs.
Familiarity with data labeling tools (Label Studio, Roboflow, CVAT).
Understanding of data-centric AI and model explainability concepts.
Experience working with cloud platforms (AWS, GCP, Azure) for ML deployment.
Exposure to MLOps pipelines and continuous model integration practices.
Knowledge of edge AI inference (e.g., NVIDIA Jetson, Coral TPU).
Experience with unsupervised or self-supervised learning approaches.
Familiarity with agricultural imaging or food quality analysis.
Contribution to open-source computer vision projects or research publications.
Understanding of model interpretability tools (Grad-CAM, SHAP, LIME).
Python,Machine Learning,Artificial Intelligence

Keyskills: studio production object detection numpy artificial intelligence cloud deep learning tensorflow library optimization gcp pytorch segmentation onnx ml deployment rest python cnn microsoft azure aiml machine learning classification transfer machine computer vision aws opencv