Secure compilation of AI generated code

Italian Ministry Of Education, University And Research; Italy; On-site; EUR 38,000 - 48,000; Full time

Job summary

The Università degli Studi di Trento invites applications for a research fellowship addressing the risks of AI-generated code. This project studies a novel theory of pluggable security patches to harden AI-produced code against memory-safety vulnerabilities and microarchitectural threats, aiming to improve software trustworthiness.

Eligibility spans multiple regions (AFRICA, EUROPE, OCEANIA, NORTH AMERICA, SOUTH AMERICA, ASIA, OTHER, EU) with a deadline of 6 Oct 2026 at 12:00 (UTC).

Job description

Organisation/Company Università degli Studi di Trento Research Field Engineering » Computer engineering Researcher Profile Recognised Researcher (R2) Leading Researcher (R4) First Stage Researcher (R1) Established Researcher (R3) Application Deadline 6 Oct 2026 - 12:00 (UTC) Country Italy Type of Contract To be defined Job Status Not Applicable Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer Description

This project addresses the risks of AI-generated code, which acts as a stochastic, untrusted compiler that translates natural language intent into often functionally correct but security-agnostic code. This project will study a novel theory of pluggable security patches to harden these AI-generated code against classical vulnerabilities (e.g., memory safety, non-interference) as well as against microarchitectural threats...

• Italy

Eligibility of fellows: country/ies of residence:

• AFRICA
• EUROPE
• OCEANIA
• NORTH AMERICA
• SOUTH AMERICA
• ASIA
• OTHER
• E.U.
• CHINA (MAINLAND)
• CHINA (HONG KONG)

Eligibility of fellows: nationality/ies:

• Contact phone: [phone]-5309