Design and Implementation of an Agentic SaaS Platform with Data Provenance for Generative Bio-Design

Internship subject

Subject 1 — PFE-01

Build the cloud platform around a generative protein-design engine, with reliable long-running jobs and a tamper-evident record of every decision.

What you’ll build

• Agentic orchestrator: Asynchronous job queues, retries and fallbacks.
• Provenance engine: Hash-chained lineage of every prompt, mutation and score.
• Enterprise console: Pareto plots and an interactive 3D molecule viewer.
• Screening and DevOps: Governance hook, Docker and open integration APIs.

Tech stack

Python, LangGraph, Docker, FastAPI, Celery, Redis, NetworkX, Next.js, PostgreSQL and 3Dmol.js.

Key challenge

Keep the audit trail consistent when jobs are retried, cancelled or partially fail.

Target

Rebuild any candidate’s full decision path in under 1 second over 10,000+ logged events.

Profile and context

• Profile: Software / AI engineering.
• Format: 1 intern, for 4 to 6 months.
• Market: Global biotech R&D.
• 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.