ServiceNow IA recherche

Mihir Bansal

Mihir Bansal

Machine Learning Engineer

Adversarial Testing & Risk Evaluation

I am a Senior Machine Learning Research Engineer at ServiceNow, working in the Adversarial Testing & Risk Evaluation squad on developing frameworks for security evaluation of LLM agents for AI Search, Recommendations and Conversational AI on the ServiceNow platform. Previously, I worked as a Machine Learning Engineer at Microsoft on improving search ranking and web search summarization using LLMs. I graduated with a Master’s degree in Data Science from Carnegie Mellon University, and from BITS Pilani with a bachelor’s degree in Computer Science and a minor degree in Data Science. I am excited about building tools for reproducible AI research, working on developing new algorithms and designing scalable software which will help in training, visualizing and evaluating machine learning models in real-time on static and dynamic datasets. I am proficient in C++, Python, C, Java, C#, R, SQL, Shell Scripting, Go, Scala, JavaScript programming languages, and have experience with frameworks such as PyTorch, Tensorflow, Keras, NLTK, OpenAI, Transformers, LangChain, OpenFace, Elasticsearch, AWS, GCP, Azure, Spark, Hadoop, Kafka, React, Angular, Kubernetes, Docker, Tableau, CUDA, A/B Testing.

Intérêts
  • Natural Language Processing
  • Machine Learning
  • AI Agents
  • Security
  • Safety
  • Open Source
  • Reinforcement Learning

Publications

DoomArena: A framework for Testing AI Agents Against Evolving Security Threats. Conference on Language Modeling (COLM),  2025.

Article Citation Code

DoomArena: A framework for Testing AI Agents Against Evolving Security Threats. Workshop at the International Conference of Machine Learning (ICML),  2025.

Article Citation Code