AI-Powered Funding Intelligence (FOA Ingestion + Semantic Tagging)

Description

Funding Opportunity Announcements (FOAs) are distributed across many agencies, vary widely in structure, and require significant manual effort to interpret and circulate. This project will build an open-source pipeline that automatically ingests FOAs from public sources, extracts structured fields, and applies ontology-based semantic tags to support institutional research discovery and grant matching.

Motivation

Research development teams often lose time and opportunities due to the manual process of finding, parsing, and categorizing FOAs. Automating FOA ingestion and tagging creates structured, queryable funding intelligence that can support investigator discovery, proposal development workflows, and institutional strategy.

Project Goals

The contributor will design and implement a modular pipeline that:

Scope of Work

1) FOA Ingestion

Build ingestion modules that scrape or retrieve FOAs from at least two sources (e.g., Grants.gov + NSF). Requirements:

2) Structured Extraction + Normalization

Extract key FOA fields including:

Output must conform to a standardized JSON + CSV schema.

3) Semantic Tagging

Implement semantic tagging aligned to a controlled ontology including:

4) Storage + Export

Deliver clean, reproducible outputs including:

5) Basic Evaluation

Create a small evaluation set to test tagging consistency and demonstrate baseline accuracy. Deliver:

Deliverables

By the end of the project, the contributor will deliver:

Stretch Goals (If Time Allows)

Required Skills

Screening Task (2-4 Hours)

Build a minimal script that ingests a single FOA URL (Grants.gov or NSF), extracts fields into the required schema, applies deterministic rule-based tags, and outputs:

Applicants should submit the following, along with a current CV or resume:

Mentors

Please DO NOT contact mentors directly by email. Instead, please email human-ai@cern.ch with Project Title and include your CV and test results. The mentors will then get in touch with you.

Corresponding Project

Participating Organizations