Grafton Sciences

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 that expand our capabilities. They are developing an at-home early detection platform for cancer, leveraging advances in synthetic biology and nanotechnology. With a $42.5 million contract from ARPA-H, Grafton aims to detect over 48 tumors at Stage I, representing a significant portion of the global cancer burden. Their approach integrates computational modeling, automated experimentation, and materials engineering, positioning them as leaders in the field of disease detection and scientific innovation.

AIAutonomous SystemsCancer DetectionHealth TechnologyMaterials EngineeringReinforcement LearningScientific DiscoverySuperintelligencegraftonsciences.com

Grafton Sciences

AIAutonomous SystemsCancer DetectionHealth TechnologyMaterials EngineeringReinforcement LearningScientific DiscoverySuperintelligencegraftonsciences.com

HQRedwood City, US

Team Size5

Open Jobs30

Total Funding-

Latest FundraiseUnknown

Join the Team

Agent Systems Engineer

On-SiteSan Francisco Bay Area, US

On-Site • San Francisco Bay Area, US

Teeming tracks opportunities at over 24,000 AI startups, then works with you to find (and land) the one you'll love.

AI Researcher

Full-timeManchester, GB

Full-time • Manchester, GB

Technical Writer

Full-timeNovi Sad, RS

Full-time • Novi Sad, RS

Backend Developer

ContractManchester, GB

Contract • Manchester, GB

DevOps Engineer

Part-timeMunich, DE

Part-time • Munich, DE

Data Scientist

Full-timeUtrecht, NL

Full-time • Utrecht, NL

Machine Learning Engineer

Full-timeRotterdam, NL

Full-time • Rotterdam, NL

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

We offer competitive salary, meaningful equity, and benefits.