Skip to content
Search jobs inside your AI agent. Claude, ChatGPT, Claude Code, Codex, Gemini, Cursor and Grok
Connect

InnoNext

Knowledge Graph for Regenerative Viticulture Planning

Posted Updated Apply by 13 views

Description

Position overview:

Build the structured reasoning layer that makes recommendations explainable and constrained by agronomic feasibility. You will design a knowledge graph (KG) schema linking practices → mechanisms → outcomes and implement a constraint-aware planner that outputs an ordered action plan with evidence links.


Problem statement (why this exists):

Even a strong model is unusable if it cannot explain “why” and respect constraints (seasonality, soil type, climate risk, operational feasibility). This track encodes domain knowledge so the engine can generate plans that are both explainable and agronomically plausible.


Data you will work with:

- Public agronomy knowledge sources (guidelines, extension material, peer-reviewed literature) transformed into structured triples and evidence links.

- Outputs from Tracks A–D to connect data-driven signals with mechanistic explanations.

- Optional internal notes/data: selected Symbioverse field observations under NDA (not required).


Key responsibilities (linked to the innovation project):

- Define an ontology/schema covering interventions, diagnostic states, mechanisms, outcomes, constraints, and evidence links.

- Create an initial KG instance from public resources and literature-derived structured knowledge.

- Implement a constraint engine (rules + graph queries) to check compatibility and feasibility.

- Prototype a lightweight plan generator that emits an ordered action plan + explanation templates.


Why your expertise is crucial:

We need someone who can turn messy domain knowledge into structured, testable representations that improve safety and trust.


Key outcomes for the Visiting Talent:

- A KG schema + example graph + query library (reusable artefact).

- Demonstration of “explainability as a product feature” for agronomy decision support.

- Experience with knowledge engineering for real-world sustainability systems.


Stream:

- Deep-Tech Talents (research-focused).

Apply

See also