Impress employers and recruiters.
Choose from hundreds of resume examples.
Impress employers and recruiters.
Choose from hundreds of resume examples.
Tailor your resume to this Research Scientist (Physical AI/Interpretability) role.
Rezi rewrites your resume against World Mechanics's job description. Free.
Tailor your resume to this Research Scientist (Physical AI/Interpretability) role.
Rezi rewrites your resume against World Mechanics's job description. Free.
Don't guess if your resume is good enough.
See how it scores against the Research Scientist (Physical AI/Interpretability) posting at World Mechanics — free, in seconds.
Don't guess if your resume is good enough.
See how it scores against the Research Scientist (Physical AI/Interpretability) posting at World Mechanics — free, in seconds.
About the Role
World Mechanics is a commercial R&D neo-lab developing interpretable foundation models of and for the physical world. We study what mechanisms world models learn about the systems they are trained on, and how to make those mechanisms more faithful to the underlying causal structure of those systems. Our goal is to build general-purpose world models that serve as reliable simulators of physical systems and can be deployed broadly across applications ranging from prediction and maintenance to robotics and scientific discovery.
Responsibilities
- Build interpretability tooling and experiments to find, test, and validate internal representations in physical AI models.
- Design “white-box evaluation” methods to detect internal failure signatures, trace model errors, and create actionable diagnostics.
- Contribute to interpretability-informed training loops, turning discoveries into training signals or inductive biases.
- Work across multimodal data (video, sensor, time-series) to determine useful representations for physical and industrial systems.
- Collaborate with the team and customers to ensure research is grounded in real deployment constraints and commercial value.
- Work toward publications at top conferences and journals, and publish open-source artifacts.
Requirements
- Strong ML research ability with demonstrated execution (papers, strong open-source, or substantial internal research impact).
- Fluency in deep learning fundamentals and the ability to prototype quickly and iterate empirically.
- Comfort working in ambiguity: ability to pick good bets, run clean experiments, and update quickly.
- Strong communication and epistemic humility.
- Interest in commercialization and product pull; care about research becoming a real capability.
Skills
- Mechanistic interpretability experience (circuits, feature discovery, attribution/causal methods, eval design).
- Experience with multimodal models, video models, robotics/embodied AI, or physical time-series.
- Experience building research infrastructure (training, eval harnesses, data tooling).
Location
- US
Work Type
- Full-time
Experience Level
- Research Scientist
Salary/Compensations
- $250,000 – $400,000
Benefits
- Competitive equity
About the Company
- World Mechanics is a commercial R&D neo-lab developing interpretable foundation models of and for the physical world.
- We focus on three connected research directions: white-box evaluation of physical models, training intrinsically interpretable foundation models for the physical world, and building interpretability-based simulators for physical systems.
- Our values include Empirical Rigor and Intellectual Openness, Ownership and Initiative, Seriousness, Kindness, and Mutual Respect, and Research with Real-World Impact.
- We pursue research with the intention of translating it into useful products and capabilities.