Job Description

About Us

The SIA-NUS Digital Aviation Corporate Laboratory aims to create and commercialise innovative technologies that could accelerate the digital transformation of Singapore\'s aviation sector, redefine the air travel experience and ensure safety and security in air travel. This will be achieved by leveraging NUS\'s world class deep tech and multi-disciplinary research expertise across artificial intelligence, machine learning, data science, operations research and analytics, optimisation, automation, sleep studies and design to develop digital technologies.



We are seeking an experienced Data Scientist or Machine Learning Engineer to join Work Package 4, which focuses on improving passenger\'s comfort, sleep and wellness. You will play a key-role in implementing cutting-edge machine learning models and algorithms to predict passengers\' cabin seat discomfort. You will work closely with hardware engineers, design researchers and project manager to successfully collect data from sensors in a cabin stimulator, and present your insights and findings to key stakeholders. Your expertise will be instrumental in combining qualitative and quantitative data from various sources, such as computer vision analysis, seat pressure mats, wearable motion sensors, and subjective discomfort ratings, to create an AI-driven solution that enhances the overall passenger experience.

Responsibilities

• Research and Development:

• Conduct in-depth research on machine learning techniques, computer vision, and data analysis methodologies applicable to cabin seat discomfort prediction.
• Stay up-to-date with the latest advancements in machine learning and AI technologies relevant to the project.
• Data Collection and Preprocessing:

• Collaborate with Hardware Engineers, Designers and Research Engineers to gather qualitative and quantitative data from seat pressure mats, wearable motion sensors, and other relevant sources.
• Analyse and develop data preprocessing pipelines to clean, normalize, and prepare data for analysis and model training.
• Model Development:

• Design and implement predictive AI models using machine learning algorithms tailored to the specific domain of cabin seat discomfort prediction.
• Utilize computer vision techniques to analyse postural data and extract relevant features.
• Combine subjective discomfort ratings with objective data to enhance model accuracy.
• Model Training and Validation:

• Train and fine-tune machine learning models using suitable training and validation strategies.
• Employ techniques like cross-validation to assess model performance and generalization capabilities.
• Real-time Integration:

• Work with software engineers to integrate the developed predictive models into real-time passenger discomfort monitoring systems on aircraft.
• Performance Optimization:

• Continuously optimize and improve the performance of AI models to ensure real-time efficiency and accuracy.

• Bachelor\'s or Master\'s degree (preferred) in Data Science, Computer Science, Engineering, and Mathematics, Statistics or a related-field.
• Proven industrial experience (3 years) in developing ML models and AI solutions for real-world applications
• Applied experience with statistical modelling (hypothesis testing), machine learning (supervised and unsupervised learning techniques) and modern deep learning architectures (CNNs, LSTMs).
• Experience with at least one programming language (with a preference for those commonly used in machine learning or scientific computing such as Python or C++)
• Proficient in digital signal processing and data analysis
• Familiar with embedded coding and iOS/Android app development
• Experience exploring, analysing, and visualising data.
• Hands-on experience using PyTorch, TensorFlow, Pandas, NumPy, Sklearn or similar machine learning/scientific libraries.
• Proficient in handling complex requirements and turn into computation logic
• Able to communicate and relay Data Science solutions adequately to business stakeholders.
• Candidate should be comfortable working on multiple projects and in a dynamic environment.
• Candidate should be able to work independently as well as be a team player.

Times Higher Education