# AI Safety & Security Researcher

**Company:** [Giskard](http://jobs.workable.com/companies/3VWw4reS2zvhrypY1FtnVA.md)
**Location:** Paris, France
**Workplace:** hybrid
**Employment type:** Full-time
**Department:** Tech

[Apply for this job](http://jobs.workable.com/view/a56aea2f-86b7-433f-b748-1ed74447161d)

## Description

Giskard defends the vision of an **AI that can be trusted** by its makers and users.

We help enterprises deploy AI with trust by **advancing research in AI safety** and providing a **leading security & quality platform for AI agents.**

Founded in **Europe**, we are Data Scientists, AI Engineers and AI Researchers who have spent years building & securing **mission-critical AI** systems for enterprises.

**Company track record**

In 2022, we raised our **first round of 1.5 million euros**, led by Elaia, with notable angel investors including Hugging Face's CTO and Mistral AI's co-founder. To read more about this fundraising, you can read [our announcement](https://www.giskard.ai/knowledge/news-fundraising-2022).

In 2023, we received a **strategic investment from the European Commission** to build a SaaS platform to automate compliance with the EU AI Act. You can [read more here](https://www.linkedin.com/posts/aniamaj_startups-smes-eueic-activity-7079083259329921025-piU_?utm_source=share&utm_medium=member_desktop).

In 2024, we won a 3 M€ grant from Bpifrance to lead research in evaluation & mitigation for LLMs, in a collaborative consortium with Mistral AI, Artefact, INA and BnF. You can learn more [here](https://www.giskard.ai/knowledge/giskard-leads-genai-evaluation-in-france-2030s-argimi-consortium).

In 2025, we launched the [Phare LLM Benchmark](https://phare.giskard.ai/) in partnership with Google **DeepMind** to evaluate LLMs across key safety & security dimensions. On the commercial side, our enterprise platform secures AI agents deployed to **millions of users** worldwide, with clients in critical industries like AXA, BNP Paribas, Michelin, Doctolib and the French government.

### About the role

We are looking for a **researcher** with an entrepreneurial mindset and **strong applied experience in Machine Learning / Artificial Intelligence**, ideally with **hands-on exposure to Generative AI / LLMs** and AI application red-teaming.  
**We are hiring people located in the EU or willing to relocate.**  

### **Your missions**

-   Design and implement robust methodologies to test, evaluate, and red-team AI agents for enterprise use cases, integrating them into our core platform.
-   Participate in red-teaming engagements and security audits of LLM-based systems, from planning attack scenarios to documenting findings and remediation paths
-   Stay ahead of emerging threats through continuous scientific watch in AI Testing, Benchmarking, and Security, and apply that knowledge to identify vulnerabilities and failure modes in LLM-based systems proactively
-   Collaborate with our engineering team to translate research concepts into production-ready code, participating in the full development lifecycle from prototyping to deployment.
-   Communicate findings with other AI teams at customers & partners, such as Mistral AI, AWS, Google, Microsoft, NVIDIA, in the form of presentations and papers.

### **What we are looking for**

**Must have**

-   Strong ML/AI knowledge, particularly around LLMs and their failure modes.
-   Solid cybersecurity fundamentals, including threat modeling and vulnerability assessment, preferably applied to AI systems.
-   Strong **written & oral communication skills** in English.

**Strong plus**

-   Demonstrated applied research experience with a focus on practical applications and tool development (papers, benchmarks, disclosed vulnerabilities).
-   Solid software engineering skills (Git, Python), including comfort directing and reviewing AI-assisted workflows.
-   Prior red-teaming, CTF, or bug-bounty experience.
-   Contributions to open-source projects.

**About you**

-   Passionate about building robust solutions to real-life problems
-   Comfortable moving between rigorous research and shipping something real that customers use
-   Hungry for learning new skills every day
-   Conscious about technology's role in our society
-   Empathetic team player

### **Recruitment process**

You can get an offer with salary & equity in 4 weeks 🚀

-   Fit interview: 20 minutes
-   Short technical exercise at home
-   Tech interview: 45 minutes
-   Final interview: 1 hour

## Benefits

We value **diversity, equity, and inclusivity**. Giskard is an equal opportunity employer. We do not discriminate on the basis of race, religion, color, origin, gender, sexual orientation, age, marital status, veteran, or disability status.

We are **remote-flex**. We value productivity and work/life balance. You can come to our office in Paris on a weekly basis if you live around Paris. You can also work remotely and come to the office on a monthly basis.

We offer a remote office kit to all full-time employees: a MacBook computer, external monitor, keyboard, mouse, etc. We also offer a very complete **health insurance plan** with Alan.

All full-time employees are granted a **significant equity package**. We want to include everyone in the adventure and make it a collective win.

**Salary:** between **60 K€ and 90 K€ / year** (**brut**) + **0.1 - 0.3% of equity**