AI security Engineer

Thales is a global technology leader trusted by governments, institutions, and enterprises to tackle their most demanding challenges. From quantum applications and artificial intelligence to cybersecurity and 6G innovation, our solutions empower critical decisions rooted in human intelligence. Operating at the forefront of aerospace and space, cybersecurity and digital identity, we’re driven by a mission to build a future we can all trust.

Thales is a major key player in Digital Security through the diversity of the security solutions proposed (Smart Cards, cloud security, applications, authentication solutions, data encryption, biometric…). The Cybersecurity team is in charge of assessing and improving the security of Thales CDI products and infrastructures. Providing safe and secure AI solutions is part of the activities of the experts of the Cybersecurity team. One of their roles is developing test methodology and providing implementation protections against cyber attacks on AI.

You will be in charge to assess the resistance of Thales AI networks against attacks (Adversarial, data poisoning…) and to design and propose innovative solutions to increase the security level of those implementations. For that purpose, you will have to master AI technologies principles, you might have implemented AI solutions and you are sufficiently familiar with AI tools to develop alone projects with Pytorch. A deep knowledge in LLM/transformer architecture and fine-tuning of any other customization methods through a past experience is required. Having a strong interest in Cybersecurity topics is also strongly recommended for the position.

Based in Noida center, working in close relationship with the others Cyber teams, you will interact with R&D Business Lines and other entities that integrate AI in their products. As the AI security domain id quickly evolving, you will need to be curious and have appetite for research activities.

Education and Experience

• Computer science engineer with dedicated course in AI
• A strong experience in fine-tuning LLM models or applying LLM based code vulnerability scanning is required (min 1 year full time on this domain) or a significant expertise in a different AI domain but with a link to CDI activites
• Cybersecurity of AI or Advanced usage of AI for security must have been demonstrated through previous projects
• 3 - 5 Years experience.

Knowledge/ Skills/Tools

Mandatory Knowledge

• -AI networks architecture
• -Knowledge in implementing AI networks
• -Linear Algebra
• -Computer arithmetic
• -very good English communication skills

Recommended Knowledge

• -AI Adversarial attacks
• -Advanced prompt injection
• -AI models architecture
• -Statistics & probabilities
• -Basic knowledge in cybersecurity

Mandatory Tools

• -Python
• -Pytorch
• -C
• -Java
• -Unix commands and scripting

Recommended Tools

-GPU programming

At Thales, we’re committed to fostering a workplace where respect, trust, collaboration, and passion drive everything we do. Here, you’ll feel empowered to bring your best self, thrive in a supportive culture, and love the work you do. Join us, and be part of a team reimagining technology to create solutions that truly make a difference – for a safer, greener, and more inclusive world.