Research Scientist, Formal Methods & AI Security

Serinyx GmbH

Saarbrücken

On-site

EUR 70,000 - 110,000

Full time

3 days ago
Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

Serinyx GmbH is seeking a Research Scientist in Formal Methods & AI Security to lead research on AI agents that reason over confidential data without leakage. You define what no leakage means and how to prove it, translating theory into a working secure link between private customer deployments and our cloud platform.

You will publish results at peer‑reviewed venues, influence the research agenda, and collaborate with engineers to deploy verification tooling and leakage estimators built from

Qualifications

  • PhD or equivalent in CS/security/cryptography with research focus.
  • Formal methods or information-flow control knowledge (non-interference, type systems).
  • Experience with statistical estimation and confidence bounds.
  • Publications in security, formal methods or ML venues.
  • Strong Python skills to run experiments.

Responsibilities

  • Define, formally, a measurable bound on what AI agents can leak and build an estimator.
  • Design the private/public link protocol and prove data cannot cross it directly.
  • Collaborate with CTO to define checks for external auditor proofs.
  • Set the measurement method, run leakage experiments and publish results.

Skills

Formal methods
Information-flow control
Statistics for estimation
Publications in security/formal-method
Python programming

Education

PhD in computer science, security, cryptography or related field

Tools

Tamarin
ProVerif
TLA+
Lean
Coq

Job description

Research Scientist, Formal Methods & AI Security

Make AI privacy provable: define, measure and prove what AI agents can leak when they reason over confidential data.

The role

You lead our research on AI agents that reason over confidential data across organisations without leaking it. You define what “no leakage” means, how to measure it and how to prove it. You also design the secure link between a private deployment on a customer’s own servers and our public cloud platform, which a distributed‑systems engineer in the team builds.

Why this role
  • An open problem where formal methods, cryptography and LLMs meet.
  • Your theory goes straight into a working system, built by an engineer in the team.
  • You lead the research agenda and write up the results for a peer‑reviewed venue.
What you will do in your first year
  • Define, formally, a measurable bound on what a debate between AI agents can leak, and build and validate an estimator for it.
  • Design the link between the private and public sides: the protocol agents use to exchange arguments across it, and the proof that protected data cannot cross it directly.
  • Design, with our CTO, how the checks that protect confidential data can be proven to an outside auditor.
  • Set the measurement method, run the main leakage measurements and write up the results for a peer‑reviewed venue.
What you bring
  • A PhD (or a submitted thesis) in computer science, security, cryptography or a related field.
  • Formal methods or information‑flow control: non‑interference, security type systems, protocol verification.
  • Statistics for estimation: confidence bounds, variance reduction.
  • Publications at strong security, formal‑methods or machine‑learning venues.
  • Enough Python to build and run your own experiments.
Nice to have

Zero‑knowledge proofs; multi‑agent LLM systems; Tamarin, ProVerif, TLA+, Lean or Coq.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Software Engineer, Distributed Systems & Security
Software Engineer, Distributed Systems & Security

Serinyx GmbH • Saarbrücken

On-site
EUR 70,000 - 110,000
LLM serving
Constrained decoding
Cryptographic engineering
+3
AI Security Researcher
AI Security Researcher

Haste • Korntal-Münchingen

Remote
EUR 90,000 - 130,000
Research Intern - AI Security
Research Intern - AI Security

Exponential Security Labs GmbH • Tübingen

Remote
EUR 8,900 - 13,000
Remote-friendly setup
Conference budget
Learning budget
+1
AI Security Researcher
AI Security Researcher

Haste • Korntal-Münchingen

Remote
EUR 90,000 - 130,000
Member of Technical Staff - AI Security
Member of Technical Staff - AI Security

Exponential Security Labs GmbH • Tübingen

Remote
EUR 90,000 - 120,000
Competitive equity
Remote-friendly setup
Conference budget
+1
Security Engineer
Security Engineer

Jobgether • Germany

Remote
EUR 80,000 - 120,000
Fully remote work
20 paid vacation days
Annual team gathering
+8
Senior AI Engineer, LLM Pipelines
Senior AI Engineer, LLM Pipelines

Serinyx GmbH • Saarbrücken

On-site
EUR 90,000 - 130,000
AI Researcher - Pre-training (f/m/d)
AI Researcher - Pre-training (f/m/d)

present of AI • Heidelberg

Hybrid
EUR 90,000 - 130,000
Research Intern - AI Security
Research Intern - AI Security

Exponential • Tübingen

Hybrid
EUR 13,000 - 20,000
Flexible hours
Remote-friendly setup
Conference budget
+1
Secure data infrastructure for AI
Secure data infrastructure for AI

Nitcservices • Berlin

Hybrid
EUR 120,000 - 180,000