VenturePulse AI: An Agentic Platform for Predictive Market Shift Forecasting in Deep Tech

Internship subject

Subject 3 — PFE-03

Identify deep-tech sectors that are about to move based on early public signals, before databases reflect those changes.

What you’ll build

• Market shift engine: Collect data from arXiv, GitHub, patent and funding feeds.
• Momentum scoring: Create an explainable, tunable score for each sector.
• Historical backtest: Assess whether the signals predicted past breakouts.
• Dashboard and briefings: Produce heatmaps, sector radar views and cited reports.

Tech stack

Python, PostgreSQL, D3.js, PyTorch, Pandas, LangGraph, Scikit-learn, FastAPI and Next.js.

Key challenge

Avoid zero lookahead bias by using strict point-in-time data from week one.

Target

Beat a funding-volume baseline on precision and recall in the backtest.

Profile and context

• Profile: AI engineering / data science.
• Format: 1 intern, for 4 to 6 months.
• Market: Global — deep tech.
• Full-time, on-site internship in Monastir, Tunisia.
• Candidates should be willing to learn and take on the challenge, have relevant skills and interests, possess an adequate level of written and spoken English, and be able to work alongside people from different backgrounds and disciplines.
• Advantages include a monthly bonus according to profile, an achievement bonus and in-demand training.