S

Research Scientist – AI Agent Privacy and Security

Visa Sponsorship
Apply Now

Lead research on what LLM-based AI agents leak when reasoning over confidential data across organizations, defining measurable bounds and testing defenses with real models. Design secure protocols between private customer deployments and public cloud, build evaluations and attack tests, and publish results at peer-reviewed venues. Requires a PhD (or submitted thesis) in CS/ML with publications, research experience on LLMs or AI agents, statistics for measurement, and Python proficiency.

Key Highlights
Lead an open research agenda on privacy of LLM-based AI agents reasoning over confidential data
Design secure protocols between private customer servers and public cloud; test that protected data cannot leak
Publish results at peer-reviewed venues; write up measurement methods and evaluations
Key Responsibilities
Lead research on AI agents built on LLMs reasoning over confidential data across organisations
Define measurable bounds on what a debate between LLM agents can leak and build and validate an estimator
Design protocols for agents to exchange arguments between private and public sides with the CTO
Build evaluations and attack tests demonstrating protection of confidential data
Run leakage measurements and write up results for peer-reviewed venues
Technical Skills Required
Large Language Models (LLMs) Python (PyTorch, Hugging Face) Statistics / Measurement (estimators, confidence bounds)
Benefits & Perks
30 days of holidays per year
International applicants supported through work-permit process (EU Blue Card)
English is the working language; German not required
Nice to Have
Privacy or security of AI systems (data leakage, membership inference, prompt injection)
Differential privacy or information-flow control
Formal methods or protocol verification (Tamarin, ProVerif, Lean)

Job Description

About Serinyx

Serinyx builds AI for high-stakes decisions on confidential data. On our decision-intelligence platform, AI agents break a hard question down, research it with checked citations and debate the findings under human review. The result is a verified, cited and signed report.

Our second product gives universities and research institutes an always-current, AI-built view of their research. We were founded in Saarbrücken in 2026 and are now building our engineering team.

The role

Want the full job description? Read the complete details on LinkedIn, the original posting.
Continue on LinkedIn

This is a short excerpt. All rights to the full description belong to its original publisher.

See Jaabz jobs first on Google 1 tap · free · in AI Overviews Jaabz is on your Google Manage Preferred Sources

Visas, Work Permits & Legal Insights

Stay informed about visa types, work permits, and immigration updates for international professionals.

Browse all articles

Subscribe to our newsletter

New visa sponsorship, relocation and remote tech jobs, delivered to your inbox.