Postdoctoral Researcher: Agentic AI and Parallel Discrete Event Simulations

What You Will Do

The Information Sciences Group (CAI-3) in the Computing and Artificial Intelligence Division at Los Alamos National Laboratory is seeking outstanding candidates for a postdoctoral research associate position at the intersection of artificial intelligence, machine learning, parallel discrete event simulation (PDES), and materials science.

Successful candidates will join a multidisciplinary team advancing materials discovery by combining theoretical methods, computational methods, machine learning and artificial intelligence. A central goal is to make use of modern generative and perturbative artificial intelligence techniques such as: large-language models (LLM), tiny recursive models (TRM), and various regression models collaborating in a human‑expert guided manner, driven by an agentic AI framework implemented over parallel discrete event simulations for extreme scalability.

The postdoctoral researcher will also explore the development of new artificial intelligence architectures, efficient training of materials models in data‑scarce scenarios, and their fast inference.

The postdoc will be mentored by staff members in the Information Sciences Group (CAI-3), and optionally co‑mentored by staff members of other groups in other divisions. We provide unique and ample opportunities for cross‑disciplinary collaborations, scientific workshop organization, and conference attendance.

Minimum

Job Requirements:

• A Ph.D. in Electrical and Computer Engineering, Computer Science, Mathematics, Materials Science, Physics, or related physical sciences, completed within the last 5 years or to be completed soon.
• Programming and simulation experience (Python, Julia, Lua, etc.)
• Demonstrated experience in conducting original scientific research through peer‑reviewed publication records.
• Excellent communication and writing skills.

Education/

Experience:

A Ph.D. in Electrical and Computer Engineering, Computer Science, Artificial Intelligence, Mathematics, Materials Science, Physics, or related physical sciences, completed within the last 5 years or to be completed soon.

Desired

Qualifications:

• Solid background in modern artificial intelligence architectures such as LLM, TRM, transformers, various machine learning frameworks, and regression methods.
• Demonstrated experience in parallel discrete event simulation (PDES) methods using Python/C/C++ frameworks such as Simian, Simulus, or similar PDES engines.
• Experience with agentic AI frameworks, Model Context Protocol (MCP) etc.
• Experience with training generative or perturbative AI models, their inference in HPC environment.
• Research experience in quantized AI models, training, and LoRA fine tuning.
• Research experience with using AI/ML methods for molecule discovery, drug discovery, and related materials science applications.
• Experience with High Performance Computing (HPC) and GPU programming, especially in the context of AI/ML. Hands‑on experience running experiments on cloud‑based HPC platforms especially for AI training and inference.
• The ability to work creatively and independently as well as learn and collaborate with experts as a part of a diverse multi‑disciplinary team.
• Ability to adapt to new requirements for projects and be flexible enough to learn new skills.

Outstanding candidates may be considered for a Director's Fellowship and for the prestigious Darleane Hoffman, Richard P. Feynman, or J. Robert Oppenheimer Fellowships. For general information refer to the Postdoctoral Program webpage.

The work location for this position is onsite and located in Los Alamos, NM. All work locations are at the discretion of management.

• Applicants must submit a CV and a cover letter detailing how they meet the minimum requirements and the desired skills for this position.
• The appointment is for a duration of two years, with the possibility of a third‑year extension based on performance evaluation.
• Candidates may be considered for a fellowship supported by the Center for Nonlinear Studies (CNLS), or the Information Sciences and Technology Institute (ISTI). Outstanding candidates may be considered for a Director's Postdoc Fellowship or for…