Location: Bangalore - Indraprastha, India

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 solid relevant professional experience.

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 Data Scientist (AI Security) (Karnataka)
🏢 Thales
📍 Karnataka