About
I’m passionate about applying cutting-edge AI technologies to solve real-world problems, and making it accessible to everyone. I built Orcheo, an easy-to-use agentic workflow orchestration platform.
My PhD in AI and diverse industry experience have sharpened my skills in developing and deploying LLM-based solutions, from research and evaluation to production workflows and user-facing products.
Research Interests
Experience
Founder
AI Colleagues
AI agent workflow and platform development, including building Orcheo for accessible agentic workflow orchestration.
Manager AI
SKIM · Rotterdam
Applied cutting-edge AI to market research, including survey bots and AI-powered data analysis.
Senior Machine Learning Scientist
Huawei R&D · Amsterdam
Reward model and PPO development; designed the Chair toolkit for SFT, RM, and PPO training; led the ChatEval challenge at DSTC 11.
Research Intern
Replika · Remote
Improved chatbot engagingness through novel dialogue modeling techniques.
Applied Science Intern
Amazon · Remote
Review summarization with the Subjective NLP team.
Publications
Weakly Supervised Turn-level Engagingness Evaluator for Dialogues
Jiang, S., Vakulenko, S., & de Rijke, M.
Proceedings of the 2023 Conference on Human Information Interaction and Retrieval (CHIIR)
A Simple Contrastive Learning Objective for Alleviating Neural Text Degeneration
Jiang, S., Zhang, R., Vakulenko, S., & de Rijke, M.
arXiv preprint arXiv:2205.02517
TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation
Jiang, S., Wolf, T., Monz, C., & de Rijke, M.
arXiv preprint arXiv:2003.11963
Improving Neural Response Diversity with Frequency-Aware Cross-Entropy Loss
Jiang, S., Ren, P., Monz, C., & de Rijke, M.
The World Wide Web Conference (WWW 2019)
Why are Sequence-to-Sequence Models So Dull? Understanding the Low-Diversity Problem of Chatbots
Jiang, S., & de Rijke, M.
Proceedings of the 2018 EMNLP Workshop SCAI
Robust Struck Tracker via Color Haar-like Feature and Selective Updating
Jiang, S., Ning, J., Cai, C., & Li, Y.
Signal, Image and Video Processing
Object Tracking via Dual Linear Structured SVM and Explicit Feature Map
Ning, J., Yang, J., Jiang, S., Zhang, L., & Yang, M.-H.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016)
Education
PhD — Open-domain Dialogue Systems
Oct 2017 – Oct 2023University of Amsterdam
Supervisors: Maarten de Rijke, Svitlana Vakulenko
Master of Engineering
Sep 2014 – Jun 2017Northwest A&F University
Thesis: Research on Feature Representation and Optimization Methods in Structured Object Tracking
Bachelor of Engineering
Sep 2010 – Jun 2014Northwest A&F University
Thesis: Implementation of Single Image Haze Removal Using Dark Channel Prior
Skills
Latest Posts
View allWhat Can Humans Learn FROM AI Models?
Exploring what humans can learn from AI models like ChatGPT, examining both technical and philosophical implications of human-AI interaction.
Fun Fact: One Good Job Offer Is All You Need
Job seekers should focus on securing a single quality offer rather than pursuing multiple positions simultaneously.
Navigating The Job Hunting Maze
Some advice on LLM job hunt in 2023, covering preparation, strategy, and understanding the nuances of the job market.
Contact
Feel free to reach out for collaborations, research discussions, or just to say hi.