Fengqing Jiang
Logo University of Washington

I am currently a 4th Ph.D. student at University of Washington under supervising of . Prof. Radha Poovendran. I am fortunate to work with Prof. Luyao Niu, and Prof. Bill Yuchen Lin at UW. I also closely work with Prof. Bo Li at UIUC and Prof. Zhen Xiang at University of Georgia.

My research interests is about building better AGI system. My works recently concentrates on LLM/Agent/LMM, topics span post-training&alignmennt/safety&security/reinforcement learning/agentic training/reasoning/data synthesis. I also worked on Machine Learning Security and Federated Learning.

If you have questions about my work, seek for collaboration, or just want to chat, feel free to contact me. Also if you are students looking for research opportunity/PhD position in our group, I am glad to help.


Education
  • University of Washington
    University of Washington
    2022 - present
    Department of Electrical and Computer Engineering
    Ph.D. Student
  • University of Illinois Urbana-Champaign
    University of Illinois Urbana-Champaign
    2018 - 2022
    B.S. in Electrical Engineering with highest honor
    Minor in Computer Science
  • Zhejiang University
    Zhejiang University
    2018 - 2022
    B.Eng. in Electrical Engineering
Experience
  • Snowflake AI
    Snowflake AI
    Research Intern
    Sept. 2025 - Current
  • Microsoft Research
    Microsoft Research
    Research Intern
    June 2025 - Sept. 2025
  • Amazon
    Amazon
    Applied Scientist Intern
    June 2024 - Sept. 2024
  • Intel AI
    Intel AI
    Machine Learning Engineer Intern
    Mar. 2022 - June 2022
Service
Student Advisory Board Member of ACTION NSF AI Institute
2023 - Current
Organizer of NeurIPS 2024 Competition, CLAS: The Competition for LLM and Agent Safety
Organizer of NeurIPS 2023 Competition, Trojan Detection Challenge 2023 (LLM Edition)
Conference Reviewer: ICML 2024/2025, NeurIPS 24, ICLR 25/26, AAAI 25/26, AISTATS 25/26, ACL 25/26
Journal Reviewer: IEEE TIFS, TNNLS
Volunteer: NAACL 2025
News
2025
💡 Invited research talk at UGA CSSI 8000: Red-Teaming for LLM Agents.
Oct 24
🏆 BadScientist received Best Paper Award at Agents4Science.
Oct 23
✈️ I am traveling to NAACL 2025 at Albuquerque, New Mexico.
May 01
🏆 SafeChain paper received Best Honorable Mention at ICLR 2025 BiAlign Workshop.
Apr 29
💡 Invited research talk at Prof. Varun Chandrasekaran group at UIUC.
Feb 20