In A Nutshell
Support faculty, postdoctoral researchers, and graduate students conducting computational and AI-driven research.
Responsibilities
- Support computational applications, software, and workflows related to climate, atmospheric, geophysical, and earth system sciences.
- Collaborate with researchers to translate scientific challenges into scalable AI/ML and computational solutions.
- Deploy, optimize, and support AI/ML pipelines on HPC and GPU-accelerated systems.
- Optimize large-scale training and inference workflows using distributed computing frameworks and performance analysis tools such as NVIDIA Nsight.
- Assist researchers with compiling, debugging, profiling, tuning, and porting scientific applications.
- Optimize system utilization, including CPU/GPU, memory, storage, and I/O performance.
- Maintain and support scientific software environments, community codes, and research datasets relevant to climate and earth system science.
- Consult with faculty and research groups to help them effectively utilize RCC, national computing facilities, and cloud resources.
- Contribute technical expertise to grant proposals and collaborative research initiatives.
- Stay informed on emerging AI methods, climate modeling advances, and GPU computing technologies relevant to Earth system science.
- Develops and presents technical training materials and web-based documentation. Ensures timely systems support and updates. Assists in conducting information security assessments and risk analysis of computing environment.
- Evaluates past and present technologies to help develop new tools. Ensures all the new tools have been through quality control reviews.
- Performs other related work as needed.
Skillset
- PhD in Computer Science, Applied Mathematics, Atmospheric Science, Physics, Earth System Science, or a related field with a strong AI/ML or computational science focus.
- Minimum of two years of relevant research or professional experience in AI/ML, scientific computing, climate science, atmospheric science, or related computational research environments.
- Strong programming skills in Python and/or C++.
- Experience with AI/ML frameworks such as PyTorch or TensorFlow.
- Experience developing, training, and optimizing neural network and deep learning architectures.
- Experience with Linux/UNIX environments and HPC systems.
- Familiarity with job schedulers such as SLURM.
- Experience deploying and optimizing workloads on GPU-accelerated systems.
- Familiarity with climate, weather, atmospheric, or Earth system data workflows and computational challenges.
- Understanding of distributed training, model scaling, and performance optimization for AI/ML applications.
- Familiarity with scientific computing libraries such as NumPy, SciPy, pandas, xarray, and scikit-learn.
- Experience working with large-scale scientific datasets and formats such as NetCDF and HDF5.
- Experience applying AI/ML methods to climate, atmospheric, or earth system science problems.
- Experience with climate and community modeling frameworks such as WRF or CESM.
- Experience with container technologies and development tools such as Git and Docker.
- Experience installing, optimizing, and profiling scientific software on HPC systems.
- Familiarity with performance analysis and compiler optimization techniques.
- Experience with distributed and parallel computing technologies such as MPI and OpenMP.
- Experience with large-scale neural network architectures for processing spatiotemporal data, such as Vision Transformers (ViTs).
- Experience with generative modeling with deep learning, such as flow matching or stochastic interpolants.
