Machine Learning Scientist, AI Explainability

About Us

At SES AI, we are at the forefront of revolutionizing lithium-metal battery creation with our groundbreaking approach that integrates cutting-edge machine learning techniques into our research and development processes. Our mission is to lead the next wave of scientific discovery in material science, powered by advanced AI technologies with a dedication to AI for Science.

To learn more about SES, please visit: www.ses.ai

Position Scope

We are a leading company specializing in the development of advanced lithium-metal batteries, on the brink of leveraging Large Language Models (LLMs) and extensive datasets to discover new battery materials. Our mission is to push the boundaries of what's possible in battery technology through innovative AI applications. To this end, the SES AI Prometheus team (AI Research) is seeking a highly skilled Machine Learning Scientist with a focus on AI explainability. This role will delve into the intricacies of large language model behavior, akin to studying the "brain" of LLMs or multimodal LLMs, utilizing causal graphs/representation, mechanistic interpretation and representation engineering tools etc. The objective is to extract the reasoning and planning capabilities of the LLMs and guide the machine towards creating innovative battery formulas.

You will be required to collaborate with strong academic labs, engaging in machine learning research aimed at addressing our battery design challenges and enhancing our systems' ability to understand and interpret data-driven science efficiently. Your contributions will be instrumental in enhancing our ability to analyze experimental data and intuitively achieve groundbreaking advancements in battery technology.

This is a remote position.

Responsibilities

• Conduct groundbreaking research on the explainability of large language models and their reasoning processes, drawing parallels with neuroscience to understand the "thought processes" of AI systems.
• Investigate the mechanisms through which LLMs approach problem-solving, planning, and solution generation, particularly in the context of basic battery design questions.
• Apply advanced techniques such as causal graphs and neuroscience-inspired AI methodologies to dissect and enhance the reasoning capabilities of LLMs, with the aim of improving accuracy and reducing instances of hallucination.
• Collaborate closely with a multidisciplinary team to integrate findings into practical AI solutions that contribute to the discovery of new battery materials and the advancement of lithium-metal battery technology.
• Contribute to academic and industry discussions by publishing research findings in top-tier journals and presenting at conferences.

Qualifications

• MS or PhD in Computer Science, Statistics, Computational Neuroscience, Cognitive Science or a related field, or equivalent practical experience.
• Strong foundational knowledge and practical experience in Machine Learning, Deep Learning, and Large Language Models.
• Proficiency in utilizing causal graphs for AI research and application.
• Demonstrated experience in AI explainability, with a focus on mechanistic interpretation and representation engineering.
• A solid track record of innovative research, preferably with published work in relevant areas.
• Proficient in programming languages relevant to machine learning, with a strong preference for Python.
• Experience with deep learning frameworks such as PyTorch or Tensorflow etc.
• Excellent problem-solving abilities and a passion for tackling complex technical challenges.
• The ability to communicate complex concepts clearly and effectively to both technical and non-technical team members.

Preferred Qualifications

• Experience with AI applications in material science or battery technology.
• Familiarity with the latest trends and methodologies in AI research, including neuroscience-inspired models and causal reasoning.