Job Title: Research Lead AI Security (Principal Scientist Equivalent)
Location: Bengaluru, India
Employment Type: Full-time

Experience: 20+ Years

Job Mode: Hybrid

Notice Period: Immediate joiner

Role Purpose

The Research Lead – AI Security is responsible for driving research within the AI Security Technology & Innovation Centre. The role focuses on advancing AI security research, translating research into validated prototypes, and driving scientific excellence in model forensics, unlearning, and AI supply-chain assurance.

Key Responsibilities

- Lead research across AI security, including model behaviour analysis, provenance, and unlearning.
- Define research hypotheses, experimental design, and validation criteria.
- Develop proof-of-concepts, benchmarks, and experimental frameworks.
- Provide technical leadership in model fingerprinting, anomaly detection, derivation analysis, and unlearning verification.
- Guide and review the work of applied researchers and research engineers.
- Collaborate with the CTO and Chief Scientist on system architecture.
- Author technical papers, research reports, and intellectual property.
- Stay current with AI security research and validate research direction.

Required Qualifications

Education

- PhD in Computer Science, Artificial Intelligence, Machine Learning, Cybersecurity, Cryptography, or a related field from a premier institute.

Experience





- 8–12+ years of experience in AI/ML research or applied security research.
- Experience leading research initiatives or complex research programs.
- Experience in R&D; labs, research projects, product companies, AI projects, enterprise solutions, or AI engineering.
- Publications in top-tier conferences (Mandatory).

Required Technical Skills

- Expertise in Large Language Models (LLMs), fine-tuning, LoRA/adapters, and Retrieval-Augmented Generation (RAG).
- Understanding of model internals, including weight-space analysis, activation patterns, and interpretability.
- Experience with AI security techniques, including fingerprinting, backdoor detection, model similarity, and provenance analysis.
- Knowledge of model unlearning methods, verification techniques, and privacy assurance.
- Proficiency in PyTorch or JAX.
- Experience with reproducible ML experimentation frameworks.

Personal Attributes

- Strong analytical mindset and scientific curiosity.
- Ability to work independently on complex research problems.
- Robust technical communication and collaboration skills.

Success Indicators

- Delivery of research outputs and proof-of-concepts.
- Contribution to AI security solution roadmaps and platform capabilities.
- Mentorship of researchers and research engineers.

📌 Research Lead AI Security (Karnataka)
🏢 Experis
📍 Karnataka