Postdoctoral In Reinforcement Learning Jobs in Chicago, IL

The Argonne Leadership Computing Facility (ALCF) is seeking a Staff Scientist in Post-Training and Reinforcement Learning for AI for Science to help advance the next generation of foundation models and learning systems for scientific discovery.

This is an opportunity to work at the frontier of AI for science and the Department of Energy Genesis mission, where large-scale machine learning, scientific data, simulation, and leadership-class supercomputers come together to enable new modes of discovery across physics, materials science, chemistry, biology, climate, energy, and related fields. We are looking for a creative and collaborative scientist who is excited to develop, scale, and evaluate post-training methods, including reinforcement learning, preference optimization, adaptation, and alignment techniques, for scientific AI models and workflows.

The successful candidate will conduct research on methods that improve the usefulness, reliability, and scientific performance of large-scale AI models after pretraining, while also advancing the systems and software needed to run these methods efficiently on cutting-edge supercomputers and emerging AI platforms. This role offers the opportunity to contribute both fundamental advances in machine learning and high-impact scientific applications while working in a multidisciplinary environment with experts in AI, simulation, computer science, applied mathematics, and domain science.

You will join the AI group - a highly collaborative, multidisciplinary environment and work alongside experts in AI, simulation, computer science, applied mathematics, and domain science. This role offers the chance to contribute both foundational advances and real-world scientific outcomes, with opportunities to publish in leading journals and conferences, engage with national and international collaborators, and influence AI and HPC for scientific research.

In this role you will:

• Conduct research and development aligned with Argonne's strategic mission in computation, AI, and scientific discovery.
• Develop, scale, and optimize post-training methods for scientific foundation models, including reinforcement learning, preference-based optimization, fine-tuning, alignment, and related approaches.
• Advance techniques that improve the performance, controllability, reliability, and scientific utility of AI models for science applications.
• Design and evaluate methods for applying reinforcement learning and post-training pipelines to large-scale scientific and data-intensive environments.
• Develop and optimize workflows for training and post-training on leadership-class supercomputers and emerging AI-oriented architectures.
• Partner with computational scientists, applied mathematicians, and domain researchers to apply foundation models and adaptive learning systems to challenging scientific problems with high impact.
• Address algorithmic, systems, and data challenges associated with large-scale training and post-training, including performance, scalability, robustness, and usability.
• Conduct original research in computational science and AI at scale, and communicate findings through publications, conference presentations, software, reports, and other research outputs.
• Work closely with colleagues across national laboratories, universities, industry, and supercomputing centers on current and future systems for the AI for science mission.
• Contribute to a team culture that values scientific excellence, collaboration, innovation, and inclusive professional growth.

This position qualifies as "Hybrid Remote Work - Mostly Onsite": which applies to employees regularly scheduled for some onsite and some remote days, with employees typically working up to 40% of their time remotely.

Position Requirements

Required Qualifications:

• RD2: Bachelor's degree and 5+ years of experience, or a Masters and 3+ years of experience, or a PhD, or equivalent
• Education in computer science, applied mathematics, statistics, computational science, or a related field
• Demonstrated advanced knowledge in one or more of the following areas: machine learning, reinforcement learning, large-scale model training, post-training, optimization, data mining, or statistics
• Strong background in mathematical optimization, linear algebra, or numerical methods
• Advanced knowledge of and significant programming experience in one or more languages such as Python, C, or C++
• Significant experience with machine learning frameworks such as PyTorch or JAX
• Experience with large-scale training, distributed learning systems, or post-training workflows
• Experience with software development practices and techniques for computational science and machine learning systems
• Ability to work effectively in interdisciplinary teams involving mathematicians, computer scientists, and application scientists
• Effective written and verbal communication skills
• Ability to model Argonne's core values of impact, safety, respect, integrity, and teamwork

Preferred Qualifications:

• Experience with reinforcement learning, policy optimization, bandits, preference learning, or related methods
• Experience with post-training methods for large models, including supervised fine-tuning, reinforcement learning from feedback, direct preference optimization, reward modeling, or model adaptation
• Experience with distributed training, large-scale optimization, and multi-node or multi-accelerator execution

Job Family

Job Profile

Worker Type

Time Type

Please note that the pay range information is a general guideline only. The pay offered to a selected candidate will be determined based on factors such as, but not limited to, the scope and responsibilities of the position, the qualifications of the selected candidate, business considerations, internal equity, and external market pay for comparable jobs. Additionally, comprehensive benefits are part of the total rewards package.

Click here to view Argonne employee benefits!

As an equal employment opportunity employer, and in accordance with our core values of impact, safety, respect, integrity and teamwork, Argonne National Laboratory is committed to a safe and welcoming workplace that fosters collaborative scientific discovery and innovation. Argonne encourages everyone to apply for employment. Argonne is committed to nondiscrimination and considers all qualified applicants for employment without regard to any characteristic protected by law.