Computer Vision / ML Engineer

Exasoft Pte. Ltd.; Singapore; On-site; SGD 70,000 - 120,000; Full time

Job summary

Exasoft Pte. Ltd. is seeking a skilled ML/Computer Vision Engineer in Singapore to train, fine-tune and evaluate models for real-world applications. You will prepare datasets, track experiments, and assess performance across various metrics, addressing errors and edge cases along the way.

You will collaborate on model packaging, deployment and governance, while maintaining comprehensive documentation and ensuring privacy and security compliance within a hospitality-focused environment.

Qualifications

• 2-6 years of experience in ML, CV, AI engineering or related areas.
• Diploma or Degree in Computer Science, AI, Data Science, Engineering, or related field.
• Strong hands-on experience with Python, deep learning and CV.
• Experience in CV areas such as Object detection, Image classification, Object tracking, Pose estimation, Video analytics.

Responsibilities

• Train, fine-tune and evaluate CV and ML models.
• Prepare and maintain datasets, experiments, evaluation results and artefacts.
• Investigate false detections, missed events, tracking errors and degradations.
• Identify edge cases and define data-labelling requirements.
• Review annotation quality and improve training data.
• Analyse lighting, camera angles, layouts and crowding affecting performance.
• Retrain models, tune thresholds and perform regression tests.
• Support packaging, versioning, deployment, release and rollback activities.
• Monitor production models and maintain performance.
• Maintain technical docs, evaluation reports and model limitations.
• Follow privacy, security, data-retention and AI-governance rules.

Skills

Python

Deep learning

Computer Vision

PyTorch

TensorFlow

OpenCV

ML lifecycle

Experiment tracking

Docker

Data annotation

Documentation

Communication

ONNX/TensorRT

GPU inference

Education

Diploma or Degree in Computer Science, AI, Data Science, or Engineering

Bachelor’s degree in related field

Tools

PyTorch

TensorFlow

OpenCV

Docker

MLflow

ONNX

TensorRT

Job description

Responsibilities

• Train, fine-tune and evaluate Computer Vision and Machine Learning models.
• Prepare and maintain datasets, experiments, evaluation results and model artefacts.
• Investigate false detections, missed events, tracking errors and model degradation.
• Identify edge cases and define data-labelling and annotation requirements.
• Review annotation quality and identify opportunities to improve training data.
• Analyse environmental factors such as lighting, camera angles, layouts and crowding that may impact model performance.
• Perform model retraining, threshold tuning and regression testing when required.
• Support model packaging, versioning, deployment, release and rollback activities.
• Monitor models in production and help maintain model performance.
• Maintain technical documentation, evaluation reports, model limitations and handover materials.
• Follow applicable privacy, security, data-retention and AI-governance requirements.

Requirements

• 2-6 years of relevant experience in Machine Learning, Computer Vision, AI Engineering or related areas.
• Diploma or Degree in Computer Science, Artificial Intelligence, Data Science, Engineering, or a related field.
• Strong hands-on experience with Python, deep learning and Computer Vision.
• Experience in at least one Computer Vision area such as Object detection,Image classification,Object tracking, Pose estimation, Video analytics.
• Experience with frameworks and tools such as PyTorch, TensorFlow, OpenCV or similar.
• Good understanding of dataset preparation and model training.
• Understanding of ML performance metrics including precision, recall, F1 score and latency.
• Ability to analyse model failures and recommend improvements to data, configuration or models.
• Familiarity with annotation tools and labelling quality checks.
• Good documentation, analytical and communication skills.
• Experience with Docker and MLOps.
• Experience with experiment tracking and ML lifecycle management.
• Exposure to ONNX, TensorRT or GPU inference.
• Experience working with production Computer Vision models.
• Exposure to video or camera-based analytics.
• Experience within hospitality or F&B environments would be advantageous but is not mandatory.