Research Engineer AI Security

Job Title: Research Engineer AI Security Location: Bengaluru, India Job Mode: Hybrid Job Type: Permanent Experience: 7- 10 Years Notice Period: Immediate joiner Role Purpose The Research Engineer AI Security is responsible for building, automating, and scaling experimental infrastructure for 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 environments for model fingerprinting, mechanistic analysis, machine 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. Prepare technical documentation, evaluation reports, and research artefacts. Required Qualifications Education B.Tech / M.Tech / MCA / BCA + MCA / MBA / M.Sc / B.Sc + MBA / MCA / M.Sc Experience 3–6+ years of experience in Research Engineering, Machine Learning Engineering, or experimentation-focused AI/ML roles. Experience supporting AI/ML research through scalable engineering systems. Required Technical Skills Strong proficiency in Python. Hands-on experience with PyTorch. Experience working with Large Language Models (LLMs), fine-tuning, and adapter-based methods (LoRA). Understanding of model internals, including parameters, activations, embeddings, and output distributions. Experience with experiment tracking, benchmarking, and reproducible research workflows. Knowledge of AI security, ML robustness, model analysis, or privacy-related techniques. Preferred Skills Experience collaborating with MLOps and backend engineering teams. Experience converting research prototypes into production-ready proof-of-concepts. Success Indicators Delivery of reliable and reproducible experimental infrastructure for AI security research. Automation and tooling that improves researcher productivity. Successful transition of research outputs into deployable proof-of-concepts and reusable platform components.