Job Title: Applied Researcher AI Security (Research Scientist Equivalent)
Location: Bengaluru, India
Employment Type: Permanent
Experience: 16 20 Years
Job Mode: Hybrid

Notice Period: Immediate joiner

Role Purpose

The Applied Researcher – AI Security will conduct applied research focused on analysing, evaluating, and strengthening AI models and AI pipelines. The role is responsible for developing validated prototypes, research artefacts, and reusable AI security techniques to build secure, compliant, and trustworthy AI systems.

Key Responsibilities

- Conduct applied research in AI security, including model behaviour analysis, provenance analysis, and model unlearning.
- Design and execute experiments, benchmarks, and comparative evaluations for AI security techniques.
- Develop proof-of-concept implementations and research artefacts.
- Analyse model internals, including weights, activations, and outputs, to identify anomalous or insecure behaviour.
- Collaborate with Research Leads and Engineering teams to operationalise research outcomes.
- Document methodologies, experimental results, and technical findings.
- Contribute to technical papers, patents, and research disclosures.

Required Qualifications

Education

- Master's or PhD in Computer Science, Artificial Intelligence, Machine Learning, Cybersecurity, Cryptography, or a related field from a Premier Institute.

Post-Doctoral candidates are preferred where applicable.

Experience





- 15–20 years of experience in Applied AI/ML Research or AI Security Research.
- Experience in R&D; labs, research projects, product companies, AI engineering, or enterprise AI solutions.
- Publications in top-tier international conferences (Mandatory).
- Proven experience in translating research concepts into validated prototypes.

Required Technical Skills

- Strong understanding of Large Language Models (LLMs) and modern machine learning architectures.
- Hands-on experience with LLM fine-tuning, LoRA, Adapter-based methods, and Retrieval-Augmented Generation (RAG).
- Strong understanding of model internals, including weight-space behaviour, activation patterns, and interpretability techniques.
- Experience with AI security techniques, including model fingerprinting, backdoor analysis, derivation detection, and behavioural testing.
- Knowledge of model unlearning, verification techniques, and privacy risk mitigation.
- Hands-on experience with PyTorch, JAX, and reproducible ML research workflows.
- Robust programming skills in Python.
- Experience working with AI/ML research codebases.

Success Indicators

- Delivery of high-quality applied research outputs and validated prototypes.
- Contributions to AI security platform capabilities and solution roadmaps.
- Recognition through research publications, patents, or intellectual property contributions.

📌 Applied Researcher AI Security (Bengaluru)
🏢 Experis
📍 Bengaluru