Internships

Danelle Cline and Duane Edgington

Automated classification of deep-sea and surface imagery: MBARI holds a rich collection of underwater video, photographs, and micrographs, much of it expertly annotated, along with aerial imagery of the ocean surface collected by drone. This intern will apply state-of-the-art computer vision methods, including foundation models, modern object detectors such as RF-DETR, and self-supervised approaches such as DINOv3, to detect and classify organisms and objects of interest to MBARI scientists, benchmarking these techniques against curated image and video collections. Successful methods will be incorporated into MBARI’s production toolset for analyzing its growing visual archive, and the work could lead to a publication. A background in computer science and proficiency in Python are required; coursework or experience in machine learning and computer vision is ideal.

Steve Haddock

Biodiversity and Bioluminescence: Steve Haddock’s lab aims to characterize and monitor the diversity and behavior of gelatinous plankton (jellyfish and their kin) in the deep sea and open ocean. For an internship project, you will choose what interests you from a related set of topics. Potential subjects include: (1) Bioluminescence biochemistry and genetics; (2) Population genetics of a zooplankton group (e.g. ctenophores, pelagic snails, siphonophores); (3) Generating interactive taxonomic keys (e.g., using Xper3); (4) Deep-sea ecology from the video annotation archives (stats and R); (5) Comparative bioinformatics and transcriptome analyses. For an overview of some unanswered questions, see our review papers (bit.ly/arms-deep and bit.ly/arms-biolum)

Kakani Katija

Bioinspiration Lab: In order to fully explore our ocean and discover the life that lives there, we need to scale up our observational capabilities both in time and space. The ocean represents the largest habitable ecosystem on our planet, yet less than 5% of that volume has been explored, and nearly 50% of marine life are yet to be described. To close this gap, scientists are increasingly leaning on underwater imaging systems and robotics to enhance their observational capacity. The Bioinspiration Lab fuses both imaging and robotics, leveraging computer vision and data science to create workflows, data pipelines, and hardware/software tools to expand our understanding of the ocean and its inhabitants in a time of great change. Interns will have the opportunity to train and deploy machine learning models on ocean visual data in real world settings (see FathomNet Database). For example, implementing SAM or instance segmentation to track specific objects with Autonomous Underwater Vehicles (AUVs) and help with occlusion and single-object isolation. Interns could also conduct human-computer interaction experiments via video gaming (see FathomVerse) or use foundation model refinement to create 3D reconstructions of animals, among other activities. Applicants with experience using Python, computer vision, machine learning, hugging face, web development, and/or embedded systems are preferred.

Lee Miller and Colleen Durkin

Characterizing mesopelagic fauna from ROV video: We are looking to work with an intern on a project utilizing remotely operated vehicle (ROV) transect footage to characterize midwater animal communities. This project will involve annotation and analysis of videos taken from the ROV SuBastian in the Southeast Atlantic, a region of the ocean where limited quantification of midwater animals has previously occurred. The intern will be encouraged to design a project focused on the aspects and members of the midwater community that are of interest to them. They will learn skills associated with video annotation, mesopelagic animal identification, and ecological community analysis. There is also the possibility for a student to learn about the use of machine learning to automate the process, if they are interested. We plan to use the FathomNet portal to facilitate detection and ID of animals in the transects.

Akshay Hinduja

Cross-Modal Learning for Underwater Perception: Sonar and optical sensors provide complementary views of the underwater world: sonar penetrates turbidity and darkness, while cameras capture fine texture at close range. Fusing these modalities remains an open challenge due to significant domain gaps and scarce labeled data. This internship will explore learning-based methods to link data across acoustic and optical sensors, leveraging 3D sonar as a shared geometric reference and source of supervision. Depending on project evolution, the intern will work with 3D sonar alongside 2D forward-looking sonar (FLS), stereo cameras, or both. Possible directions include cross-modal feature matching, training 2D FLS models with 3D sonar supervision for occupancy mapping and obstacle avoidance, and transferring geometric priors from sonar to stereo imagery. Working with field data collected by MBARI’s underwater vehicles, the intern will gain hands-on experience in multimodal fusion, deep learning for perception, and field robotics research. Candidates should be proficient in Python and PyTorch, with coursework or project experience in computer vision and machine learning. Familiarity with sonar data, point clouds, or 3D geometry is a plus.

Rebecca Englert

Environmental Signals from Ocean Bottom Seismometers: Ocean bottom seismometers measure ground motion and are conventionally used to study earthquakes. However, a wide range of processes in the ocean produce small-scale ground motion that can also be recorded by seismometers placed on the seafloor. These include vibrations created by ocean currents, acoustic waves (e.g., whale calls, vessel noise), and mass movements. Thus, these instruments have significant untapped potential to contribute to our understanding of biology, geology, and physical dynamics in the ocean. We are looking for an intern to explore a dataset from a 4-month long deployment of an array of ocean bottom seismometers in the Monterey Canyon. The intern will identify and analyze environmental signals and compare them with other datasets that were collected simultaneously. Candidates with experience programming in Python are preferred.

Kobun Truelove

Oceanomics Lab: This internship is based in MBARI’s Oceanomics Lab, a centralized, state-of-the-art molecular biology lab available to all research teams at MBARI. The lab supports advanced techniques such as environmental DNA (eDNA), environmental RNA (eRNA), target capture sequencing, and long-read sequencing with the goal of fostering innovation, collaboration, and scientific discovery at MBARI.
The intern will have the option of collecting samples at sea aboard research vessels and will have access to samples collected from long-range autonomous underwater vehicles (LRAUVs) and remotely operated vehicles (ROVs). The project will involve sequencing these samples using nanopore sequencing methods and analyzing the resulting data to characterize marine biodiversity. Along the way, the intern will gain hands-on experience in molecular laboratory techniques, data analysis, and bioinformatics.
Applicants with previous molecular experience in one or more of the following areas are preferred: preparing environmental samples for DNA sequencing, working with DNA or RNA sequence data, nanopore sequencing, and bioinformatics.

Emme Wiederhold

Operations Dashboard for Fleet of Long-Range AUVs: MBARI hosts a fleet of Long-Range Autonomous Underwater Vehicles with various instruments and science goals, providing an essential observation platform for exploring the complex biological and physical processes of our changing oceans. All of these vehicles are operated via a web user interface, which supports monitoring of fleet health, sending of new missions and commands, exploring data on shore, and more. The team is looking to add even more capabilities to increase pilot efficiency, improve situational awareness, and maximize science through vehicle autonomy. We are looking for an intern with a background in computer science, notably TypeScript and React, and an interest in complex underwater systems, who will contribute to this unique user interface.

Giancarlo Troni and Sebastian Rodriguez

Scalable Marine Robotics: Ocean exploration has been widely developed thanks to marine robotics, whose platforms are currently being used on several applications, such as accurately mapping the seafloor in high-resolution and continuously tracking animals in midwater. However, these platforms are not scalable, many are still too expensive to build and operate, and access to scientists, and therefore ocean exploration and discovery, is limited due to underwater vehicle navigation among others. Potential intern projects will use current MBARI’s robotics platforms to enable scalable marine robotics navigation in complex terrain. Efforts include sensor calibration and alignment of sensor data and visual-inertial navigation based on simultaneous localization and mapping (SLAM) framework. The work will combine elements of estimation, computer vision, software development and data analysis. Candidates should have basic competence in C/C++ and Python programming. Experience with robotics will be advantageous.

John Ryan, Duane Edgington, Danelle Cline

Soundscape: Marine animals use sound in essential life activities, including communicating, socializing, foraging, navigating, and reproducing, so recording and analyzing sound in the ocean provides a profound window into their lives. MBARI’s recordings from the MARS cabled hydrophone, in the heart of Monterey Bay National Marine Sanctuary, have expanded our knowledge of regional biodiversity and revealed complex and beautiful dimensions of animal behavioral ecology. In summer 2027, the intern will apply Google DeepMind’s Perch 2.0 bioacoustic foundation model and the perch-hoplite agile-modeling toolkit to years of these deep-sea recordings, building and refining classifiers that detect whales, dolphins, and other sounds, and synthesizing those results with an understanding of the ecosystem in which the animals live. Along the way, the intern will gain hands-on experience in machine learning, signal processing, and marine science, mentored by scientists and software engineers who are actively collaborating at this exciting frontier.