Research Engineering/ Scientist Assistant – Deep Learning for Structural Biology Part-time NEW

Research Engineering/ Scientist Assistant – Deep Learning for Structural Biology

The Oden Institute is an organized research unit that fosters interdisciplinary programs in computational sciences and engineering, computational medicine, computational geosciences, mathematical modeling, applied mathematics, data science, artificial intelligence, software engineering, and computational visualization.

The University of Texas at Austin is a nationally ranked, tier-one research institution and one of the largest employers in central Texas. UT is located in the heart of Austin, a vibrant city that frequently appears on lists of best cities to live and work. Committed to recruiting and retaining a varied and talented workforce, the university offers competitive salaries and benefits, an extensive support network, and above all, an enriching and highly collaborative community that is deeply passionate about our vision for higher education and public service.

UT Austin offers a competitive benefits package that includes:

• 100% employer-paid basic medical coverage
• Retirement contributions
• Paid vacation and sick time
• Paid holidays

Please visit our Human Resources (HR) website to learn more about the total benefits offered.

NOTE: This position is initially appointed for a six-month term. Continuation beyond the initial six-month assignment is contingent upon funding availability and satisfactory performance.

Purpose

We are inviting highly qualified individuals to join our research group at the Oden Institute, University of Texas at Austin. This is a competitive opportunity for individuals with proven deep learning expertise and a strong interest in pioneering applications in computational biology.

Responsibilities

The selected candidate will be involved in the development, implementation, and evaluation of deep learning methods for structural biology and molecular modeling. Depending on experience and project needs, responsibilities may include:

Research

• Developing and applying deep learning models for predicting protein structures and molecular interactions
• Exploring model architectures and training approaches, including geometric deep learning, diffusion models, and graph neural networks
• Preparing and processing biological and structural datasets for model training and evaluation
• Implementing and maintaining research code and computational workflows
• Training, fine-tuning, and evaluating models using GPU and high-performance computing resources
• Designing computational experiments to assess model accuracy, efficiency, and generalization
• Comparing model performance with existing methods using appropriate benchmarks and evaluation metrics
• Investigating model limitations and exploring ways to incorporate physical and biological information
• Reviewing relevant scientific literature and adapting promising methods to ongoing research

Research documentation and communication

• Documenting methods and experiments to support reproducibility

Research coordination and collaboration

• Preparing figures, reports, presentations, and contributions to scientific publications
• Collaborating with researchers in computational biology, biochemistry, and biophysics to guide model development and interpret results

Required Qualifications

• Bachelor's Degree in a relevant or related field
• Strong experience in deep learning, especially in: Geometric Deep Learning
• Diffusion Models, and Related areas such as graph neural networks, equivariant architectures, and generative modeling
• Proficient programming skills and familiarity with modern machine learning frameworks

Preferred Qualifications

• Interest or background in biological or structural applications

Salary Range

$3,000 monthly (50% Full Time Equivalent)

Working Conditions

• May work around standard office conditions
• Repetitive use of a keyboard at a workstation
• Use of manual dexterity

Required Materials

• Resume/CV
• 3 work references with their contact information; at least one reference should be from a supervisor
• A brief description of your research interests and relevant experience, and any examples of previous computational or structural biology work.