Postdoctoral Fellow

University of Texas at Austin • Austin, TX

5d • Hybrid

About The Position

The University of Texas at Austin’s Department of Marine Science and the Marine Science Institute, in collaboration with the Department of Computer Science’s Computer Vision group, invite applications for an exciting postdoctoral position at the intersection of marine ecology, ocean technology, machine learning, and high-throughput biological imaging. This position offers a rare opportunity to help pioneer the use of advanced shadowgraph imaging systems for studying the transport and behavior of plankton and larval organisms in dynamic and estuarine environments. The successful candidate will help develop and validate AI-driven pipelines for the detection, segmentation, classification, and tracking of zooplankton and estuarine-dependent larvae in noisy, high-volume imaging datasets collected under challenging field conditions. The work will involve applying state-of-the-art machine learning approaches to classify organisms despite cluttered imagery, marine snow, suspended particles, and subtle morphological differences among taxa. This position will be located in Austin, TX.

Requirements

• PhD in Computer Science or Electrical Engineering received within the last 3 years.
• Essential experience includes Python, modern techniques in visual recognition and image segmentation, and the ability to rapidly prototype and fine-tune open-source computer vision models

Nice To Haves

• Candidates with expertise in computer vision, AI/machine learning, and data science are encouraged to apply.

Responsibilities

• Developing automated image-analysis workflows; implementing visual validation protocols
• Exploring active learning and crowdsourced annotation approaches
• Quantifying organism movement and behavior through image tracking
• Advancing unsupervised and semi-supervised classification methods to discover previously unrecognized biological groupings
• Explore adaptive AI-guided imaging strategies, including reinforcement-learning approaches that dynamically optimize sampling based on environmental conditions such as turbidity and currents
• Lead the preparation of manuscripts for submission to high-impact peer-reviewed conferences and journals
• Contribute to the intellectual development of students and junior researchers

Benefits

• Teacher Retirement System of Texas (TRS)
• Optional Retirement Program (ORP)

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level
• Education Level: Ph.D. or professional degree