Research Fellow (AI-Assisted Anomaly and Stress Detection for Controlled Environmental Aquaculture)

Job Details

In this job opening, we are seeking a highly motivated and visionary researcher to join our team focused on AI and data science in controlled environmental aquaculture. This role involves research and development in AI-assisted methods for anomaly and fish stress detection, aiming to demonstrate early disease warning platforms outperforms traditional approaches. We invite applicants to join us as a Research Fellow (full-time). You will be part of the Fraunhofer-NTU Research Centre in collaboration with the NRF CREATE programme Singapore Aquaculture Solution Centre SAS-C.

Key Responsibilities
 

• Research and develop AI-assisted methodologies and tools for anomaly and stress pattern detection in aquaculture systems.
• Focus on multi-modal sensor data integration and AI models tailored for fish behaviour, health, and stress signal analysis.
• Investigate and apply novel machine learning and deep learning techniques for pattern recognition, classification, and early intervention alerts in aquatic environments.
• Integrate open-source and commercial aquatech tools (e.g., air and underwater imaging, biosensor platforms) to build proof-of-concept detection pipelines.
• Investigate and build robust data and AI agent pipelines for continuous learning and knowledge acquisition, including annotation strategies and knowledge graph development for aquaculture stress events.
• Design AI-guided decision-making pipelines to support early warning systems, predictive health management, and mitigation of stress-induced anomalies
• Co-develop benchmarking frameworks and stress test environments to evaluate model accuracy, false-positive rates, and real-time system responsiveness.
• Collaborate closely with international renowned biologists, aquaculture domain experts, sensor engineers, and AI developers to deploy and validate stress detection systems in operational environments.
• Publish research outcomes with the team in leading conferences and journals in AI, aquaculture, bio technology, and environmental monitoring.
• Contribute to white papers and strategic roadmaps to guide long-term development of intelligent aquaculture monitoring systems.

Requirements

Job Requirements
 

• PhD in Computer Science, AI, Bioengineering, Electrical/Electronic Engineering, Environmental Informatics, or a related field with focus on intelligent systems or biological sensing.
• Proven experience with sensor integration, data acquisition systems, and embedded hardware prototyping, preferably in aquatic or environmental monitoring contexts.
• Strong understanding of real-time digital signal processing, control systems, and embedded AI for biological applications.
• Experience with AI/ML development frameworks, model deployment pipelines, and simulation environments for behavior or anomaly detection in living organisms.
• Proven expertise in machine learning for time-series, video, or biosignal analysis; familiarity with reinforcement learning, agentic AI, or domain-adapted LLMs is highly advantageous.
• Familiarity with fish physiology, aquaculture stress indicators, or environmental sensing systems is beneficial; prior work in biosignal processing or environmental anomaly detection is a plus.
• Track record of research publications in top-tier venues in AI, aquaculture, bioinformatics, or environmental monitoring is strongly preferred.
• Strong analytical and problem-solving abilities
• Demonstrated ability to work across interdisciplinary and diverse teams, ideally with experience in project planning and management
• Excellent collaborative and communication skills in English for research purposes
• Good communication and presentation skills, fluency in multiple languages is a plus
   

We regret that only shortlisted candidates will be notified.

Contact Information

https://ntu.wd3.myworkdayjobs.com/Careers/job/NTU-Main-Campus-Singapore/Research-Fellow--AI-Assisted-Anomaly-and-Stress-Detection-for-Controlled-Environmental-Aquaculture-_R00021511/apply