Postdoctoral Research Associate

The Scientific Computing Applications group in CSD has an immediate opening for a Postdoctoral Research Associate to design, develop, and deploy machine-learning and high-performance computing workflows, algorithms, and software in support of Department of Energy (DOE) mission applications across a broad range of scientific domains, including materials, biology, physics, and nuclear science. The successful candidate will partner closely with domain scientists to co-develop and apply cutting-edge machine learning and computational techniques to address scientific computing needs such as scalable ML training and inference, surrogate modeling of scientific processes, workflow automation and adaptive simulation pipelines, and performance analysis and optimization. The candidate will also contribute to and help originate research and proposal ideas in collaboration with staff scientists, supporting both their professional development and the goals of the Laboratory.

The appointment will be initially for two years, with the possibility of extension and career growth contingent on performance and funding.

Essential Duties and Responsibilities:

• Work collaboratively with computer scientists, computational scientists, applied mathematicians, and domain scientists
• Develop software that integrates machine learning and numerical techniques targeting heterogeneous architectures (GPUs and accelerators), including DOE leadership-class supercomputing facilities, to enable and support scientific research
• Identify and implement strategies for correctness and reproducibility testing, and analyze and optimize software scalability and performance
• Apply software engineering and documentation best practices to ensure usability and maintainability
• Present results at meetings, workshops, and conferences
• Publish findings in conference proceedings and/or peer-reviewed journals

Required Knowledge, Skills, and Abilities:

• PhD in Computational Physics, Chemistry, Materials Science, Computer Science/Engineering, Applied Mathematics, or a related field.
• Strong experience developing, deploying, and optimizing applications and workflows in high-performance computing (HPC) environments.
• Demonstrated programming proficiency in C/C++ (preferred) and Python, with experience in additional languages such as Fortran considered a plus.
• Strong knowledge of at least one parallel programming model commonly used in HPC, such as MPI, OpenMP/OpenACC, CUDA, HIP, Kokkos, or SyCL/OpenCL.
• Hands-on experience with machine learning, including end-to-end training, tuning, and evaluation of at least one class of models.
• Working understanding of common machine learning model classes and their roles in scientific applications, such as deep neural networks (DNNs), convolutional neural networks (CNNs), transformer models, and graph-based neural networks.
• Familiarity with software engineering best practices, including testing, documentation, source code management, and release procedures.
• Effective written and verbal communication skills, including the ability to work productively with interdisciplinary teams.

Preferred Knowledge, Skills, and Abilities:

• Experience scaling machine learning training and/or inference on multi-node HPC systems.
• History of implementing, adapting, or optimizing machine learning architectures for scientific or high-performance computing applications.
• Background in software performance evaluation, profiling, and optimization on CPUs and GPUs.
• Knowledge of common numerical algorithms used in scientific computing, such as linear solvers, optimization methods, or stochastic sampling techniques (e.g., Markov Chain Monte Carlo).
• Experience developing or using advanced computational workflows, including adaptive, automated, or agent-based (agentic) workflows that integrate simulation, data analysis, and/or machine learning.
• Experience with computational workflows on large-scale HPC systems, including leadership-class or pre-exascale/exascale platforms such as Perlmutter, Frontier, or Aurora.
• Contributed to collaborative or open-source software projects.

Additional Information:

• Moderate domestic and international travels are expected.
• This is an on-site position at the Upton, NY campus, with the possibility of hybrid work arrangements.
• BNL policy requires that after obtaining a PhD, eligible candidates for research associate appointments may not exceed a combined total of 5 years of relevant work experience as a post-doc and/or in an R&D position, excluding time associated with family planning, military service, illness or other life-changing events.
• PhD must be obtained prior to commencing employment.
• Brookhaven National Laboratory is committed to providing fair, equitable and competitive compensation. The full salary range for this position is $71,900 - $119,000 / year. Salary offers will be commensurate with the final candidate's qualification, education and experience and considered with the internal peer group.
• Brookhaven National Laboratory is committed to employee success and we believe that a comprehensive employee benefits program is an important and meaningful part of the compensation employees receive. Review more information at BNL | Benefits Program