
Grafton Sciences is focused on building physical superintelligence to accelerate scientific discovery. Their mission is to create systems capable of autonomous scientific discovery, utilizing tools…

Grafton Sciences is focused on building physical superintelligence to accelerate scientific discovery. Their mission is to create systems capable of autonomous scientific discovery, utilizing tools…
Your next opportunity is in here somewhere. Sign up to explore 70,000+ startups and their open roles. No spam. No gamification. Just jobs.
70,000+
Startups
83,000+
Open Roles
4,600+
New This Week
About Grafton Sciences
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.
About the Role
We’re seeking a Agent Systems Engineer to design and implement the planning, orchestration, and tool-use behaviors that enable LLMs to reliably operate complex engineering workflows. You’ll build LangGraph planners, deterministic execution flows, action schemas, recovery strategies, and cross-tool interfaces that allow agents to reason over multi-step tasks with safety and reproducibility. This role is for someone who thrives at the intersection of language models, structured schemas, tool interfaces, and real system constraints.
Responsibilities
• Build agent planners, tool-call flows, and state machines using LangGraph or similar frameworks.
• Design schemas, action adapters, and cross-tool interfaces that enable deterministic, traceable LLM tool use.
• Implement error handling, timeout strategies, retries, rollbacks, and replay mechanisms for robust agent behavior.
• Collaborate closely with systems architecture, data infrastructure, and ML teams to integrate agents into real engineering toolchains.
Qualifications
• Strong experience building agent systems, LLM tool-calling pipelines, or structured orchestration frameworks.
• Deep intuition for schemas, action abstractions, reproducibility, and deterministic execution of multi-step workflows.
• Ability to reason about system-level failure modes, edge cases, and safe tool interaction in complex environments.
• Comfortable working across AI, systems engineering, and domain-tooling interfaces in a fast-moving, high-precision setting.
Above all, we look for candidates who can demonstrate world-class excellence.
Compensation