Data Scientist (AI Security)

Location: Bangalore - Indraprastha, India

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.

Present in India since 1953, Thales is headquartered in Noida and has other operational offices and sites spread across Delhi, Gurugram, Bengaluru and Mumbai, among others. Over 2200 employees are working with Thales and its joint ventures in India. Since the beginning, Thales has been playing an essential role in India’s growth story by sharing its technologies and expertise in Defence, Aerospace and Cyber & Digital sectors. Thales has two engineering competence centres in India - one in Noida focused on Cyber & Digital business, while the one in Bengaluru focuses on hardware, software and systems engineering capabilities for both the civil and defence sectors, serving global needs. The Group has also established an MRO (Maintenance, Repair & Overhaul) facility in Gurugram to provide comprehensive avionics maintenance and repair services to Indian airlines and support the growth of the local aviation industry.

Data Scientist (AI Security)

Thales - Imperva is seeking a Data Scientist to join our AI Protection initiative in India. Our team focuses on securing the next generation of AI‑powered applications and generative AI platforms. We are building and advancing our AI Firewall (AIFW) to help organizations detect and mitigate emerging threats targeting Large Language Model (LLM) systems and AI agents.

This role focuses on data‑centric AI: designing high‑quality datasets and evaluation frameworks that directly improve detection performance. You will work closely with Security Researchers who discover new attack techniques and with Data Scientists and ML engineers who develop detection models. Your work will transform emerging AI threats into structured datasets and evaluation benchmarks that strengthen our ability to detect attacks such as prompt injection, jailbreaks, model manipulation, and sensitive data exfiltration.

What will you do?

• Build and maintain datasets used to train and evaluate AI security detection models.

  
  

• Collaborate with Security Researchers to convert newly discovered attack techniques, jailbreak strategies, and adversarial prompts into structured datasets and labeling guidelines.

  
  

• Design scalable workflows for collecting, generating, curating, and maintaining high‑quality datasets.

  
  

• Implement dataset quality processes such as filtering, deduplication, sampling, and continuous updates as the threat landscape evolves.

  
  

• Define evaluation datasets and benchmarks to measure detection performance and track model improvements over time.

  
  

• Generate synthetic and adversarial prompts to expand coverage of emerging attack techniques.

  
  

• Work closely with engineers and data scientists to integrate datasets and evaluation workflows into model experimentation, training, and production pipelines.

  
  

• Analyze detection performance and recommend improvements to datasets, labeling strategies, and model training approaches.

  
  

Requirements

• 4–7 years of industry experience as a Data Scientist working on machine learning or data‑driven systems.

  
  

• Background in application security, adversarial machine learning, or AI safety.

  
  

• Strong Python skills and experience working with large datasets using tools such as Pandas, SQL, Spark, or similar platforms.

  
  

• Experience building datasets and evaluation pipelines for machine learning models.

  
  

• Familiarity with NLP, LLM systems, or generative AI technologies.

  
  

• Ability to collaborate effectively with researchers, engineers, and product teams and communicate technical insights clearly.

  
  

Preferred Qualifications

• Experience creating synthetic, adversarial, or security‑focused datasets.

  
  

• Experience with modern ML/LLM frameworks such as Hugging Face, PyTorch, TensorFlow, or Scikit‑learn.

  
  

• Experience with cloud platforms such as AWS, Azure, or GCP.

  
  

• Familiarity with Kubernetes, data pipelines, or production ML infrastructure.

  
  

• Experience with ML lifecycle practices including CI/CD, experimentation, and model monitoring.

  
  

Education

• Ph.D. or M.Sc. in Computer Science, Engineering, Mathematics, or a related technical field is preferred but not required if you have strong relevant professional experience.

  
  

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.