Senior Neuro-Symbolic Systems Engineer

Grafton Sciences•San Francisco, CA

22d

About The Position

We’re building physical general intelligence — autonomous systems that can experiment, reason, and discover in the physical world. With deep technical roots and real-world progress at scale (e.g., a $42M NIH project), we’re pushing the frontier of physical AI. Joining us means inventing from first principles, owning real systems end-to-end, and helping build a capability the world has never had before. We’re building AI systems with general physical ability — the capacity to experiment, engineer, or manufacture anything. We believe achieving this is a key step towards building superintelligence. With deep technical roots and real-world progress at scale (e.g., a $42M NIH project), we’re pushing the frontier of physical AI. Joining us means inventing from first principles, owning real systems end-to-end, and helping build a capability the world has never had before. We’re seeking a Senior Neuro-Symbolic Systems Engineer to design and build the graph-based representations that underpin autonomous reasoning and decision systems. You’ll work on symbolic and relational structures (for example, hypergraphs, dynamic rule systems, and structured planning representations) that allow agents to model complex environments, update internal state, and coordinate across tools and workflows. This role blends ML, symbolic reasoning, and systems engineering.

Requirements

Strong background in symbolic AI, knowledge representation, graph systems, computational logic, or neuro-symbolic methods.
Experience designing or implementing structured representations for planning, reasoning, or complex workflows.
Familiarity with ML toolchains and comfort bridging symbolic and statistical systems.
Ability to design abstractions and system architectures that support large-scale, real-time updates.
High-agency engineer who enjoys defining new structures and building them from first principles.

Responsibilities

Design and implement structured representations such as hypergraphs, relational models, symbolic planners, or similar abstractions.
Build update rules, inference mechanisms, and dynamic graph operations that support multi-step reasoning and coordination.
Work with agent, simulation, and data infrastructure teams to integrate symbolic structures into real workflows.
Develop tools for evaluating correctness, consistency, and stability of graph-based representations.
Operate as a cross-functional technical partner to ensure symbolic layers work alongside ML, RL, and systems architecture components.