LLMs For Decision Making Co-Op (AI)

TL;DR

LLMs For Decision Making Co-Op (AI): Developing algorithms that drive experimental decision-making in physical and life sciences with an accent on combining LLM reasoning with Bayesian optimization. Focus on building evaluation frameworks, prototyping LLM-augmented strategies, and integrating these into the AI Science Facilities decision stack.

Location: Cambridge, MA, USA (Onsite)

Company

hirify.global builds Scientific Superintelligence to accelerate discovery across physical and life sciences via autonomous AI systems.

What you will do

• Develop LLM-based decision-making methods for scientific experimental campaigns.
• Prototype approaches combining LLM reasoning with Bayesian optimization and active learning.
• Build evaluation frameworks to benchmark LLM-augmented strategies against Bayesian baselines.
• Integrate optimized methods into the production decision-making stack.
• Document research findings and contribute to internal libraries.

Requirements

• Pursuing a Master's or PhD in ML, Computer Science, Statistics, Physics, Chemistry, or related quantitative fields.
• Strong proficiency in Python and ML frameworks such as PyTorch or JAX.
• Solid foundation in Bayesian methods and probabilistic modeling.
• Experience with LLM fine-tuning, test-time compute, and benchmarking in applied settings.
• Ability to translate open-ended scientific questions into concrete ML tasks with clear metrics.
• Must be based in or able to work onsite in Cambridge, MA, USA.

Nice to have

• Experience with multi-objective optimization or batch Bayesian optimization in scientific settings.
• Familiarity with agentic frameworks and structured-output techniques for scientific reasoning.
• Exposure to materials science, chemistry, catalysis, batteries, or electrochemistry.
• Prior experience pairing LLMs with planning or decision processes.

Culture & Benefits

• Fast-paced startup environment focused on solving historic challenges in medicine, materials, and energy.
• Core values based on truth, trust, curiosity, grit, and velocity.
• Opportunity to work at the intersection of AI and physical sciences.
• Collaborative culture across ML and physical science teams.