Role : Research Engineer - AI Security

Location : Bengaluru, India

Function : AI Security - Technology & Innovation Centre (TIC)

Employment Type : Full-time

Role Purpose :

The Research Engineer - AI Security is responsible for building, automating, and scaling experimental infrastructure that enables rigorous, reproducible AI security research. The role focuses on experiment automation, benchmarking, and research-to-solution engineering to support secure, compliant, and trustworthy AI systems.

Key Responsibilities :

- Design and implement reproducible experiment pipelines for AI security research.

- Build automation frameworks for benchmarking, ablation studies, and large-scale model evaluations.

- Develop experimental benches for model fingerprinting, mechanistic analysis, unlearning, and provenance.

- Translate research prototypes into engineering-grade proof-of-concepts and reusable components.

- Collaborate with applied researchers, backend engineers, and MLOps teams to enable deployment-ready solutions.

- Maintain experiment tracking, versioning, and validation to ensure reliability and auditability.

- Contribute to technical documentation, evaluation reports, and research artefacts.

Required Qualifications & Experience :

Education :

- Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, or a related engineering discipline.

Experience :

- 3 - 6+ years of experience in research engineering, ML engineering, or experimentation-heavy roles.

- Hands-on experience supporting AI/ML research with scalable engineering systems.

Required Technical Skills :

- Strong proficiency in Python and deep learning frameworks such as PyTorch.

- Experience working with large language models, fine-tuning workflows, and adapter-based methods (e.g., LoRA).

- Understanding of model internals including parameters, activations, embeddings, and output distributions.

- Experience with experiment tracking, benchmarking, and reproducible research workflows.

- Familiarity with AI security, ML robustness, model analysis, or privacy-related techniques is desirable.

Success Indicators :

- Delivery of reliable, repeatable experimental infrastructure supporting AI security research.

- Effective enablement of applied researchers through automation and tooling.

- Successful transition of research outputs into deployable proof-of-concepts or platform components