I am a Software Engineer at Databricks, bridging the gap between foundational AI research and production. I focus on code intelligence and AI agents, taking concepts from early prototypes to shipped products.

  • Databricks Assistant Autocomplete

    AI-powered code completion that understands your context to suggest relevant, accurate code as you type. From an early idea to Generally Availability, driving data collection, model training, custom evaluation frameworks, and continuous production improvements.

  • Genie Code

    Autonomous AI partner for data work. Rigorous evaluation systems and continuous quality improvements to ensure precise, reliable code execution.

Before joining Databricks, I earned my PhD in Computer Science from University College London (UCL). My research focuses on building accurate and efficient AI systems, particularly for question answering and knowledge retrieval, to help people access the most relevant and up-to-date information in real-world settings. During my PhD, I was a Research Scientist Intern at DeepMind, where I worked with Arthur Mensch and Igor Babuschkin on Retrieval-Enhanced Transformer (RETRO). I also worked as a Research Intern at Salesforce Research, where I collaborated with Caiming Xiong on dialogue summarization and knowledge distillation.

Education

  • 2020 – 2024Ph.D. in Computer Science, University College London
    Advised by Pontus Stenetorp and Sebastian Riedel
  • 2018 – 2020MMath in Computer Science, University of Waterloo
    Advised by Jimmy Lin
  • 2013 – 2017B.Eng. in Software Engineering, Tongji University

Experience

  • 2023 – PresentDatabricks, Research Engineer · Mountain View, US
  • 2022 – 2022 DeepMind, Research Scientist Intern · London, UK
  • 2019 – 2020Salesforce Research, Research Intern · Palo Alto, US

Selected Publications

  1. What the DAAM: Interpreting Stable Diffusion Using Cross Attention Raphael Tang*, Linqing Liu*, Akshat Pandey, Zhiying Jiang, Gefei Yang, Karun Kumar, Jimmy Lin, Ferhan Ture. ACL 2023 (Best Paper Award)
  2. Challenges in Generalization in Open Domain Question Answering Linqing Liu, Patrick Lewis, Sebastian Riedel, Pontus Stenetorp. NAACL 2022
  3. When Do Flat Minima Optimizers Work? Jean Kaddour*, Linqing Liu*, Ricardo Silva, Matt J. Kusner. NeurIPS 2022
  4. PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them Patrick Lewis, Yuxiang Wu, Linqing Liu, Pasquale Minervini, Heinrich Küttler, Aleksandra Piktus, Pontus Stenetorp, Sebastian Riedel. TACL 2021
  5. Controllable Abstractive Dialogue Summarization with Sketch Supervision Chien-Sheng Wu*, Linqing Liu*, Wenhao Liu, Pontus Stenetorp, Caiming Xiong. ACL 2021
  6. MKD: A Multi-Task Knowledge Distillation Approach for Pretrained Language Models Linqing Liu, Huan Wang, Jimmy Lin, Richard Socher, Caiming Xiong. arXiv preprint, 2020
  7. Incorporating Contextual and Syntactic Structures Improves Semantic Similarity Modeling Linqing Liu, Wei Yang, Jinfeng Rao, Raphael Tang, Jimmy Lin. EMNLP 2019
  8. Bridging the Gap between Relevance Matching and Semantic Matching with Hierarchical Co-Attention Network Jinfeng Rao, Linqing Liu, Yi Tay, Wei Yang, Peng Shi, Jimmy Lin. EMNLP 2019
  9. Distilling Task-Specific Knowledge from BERT into Simple Neural Networks Raphael Tang*, Yao Lu*, Linqing Liu*, Lili Mou, Olga Vechtomova, Jimmy Lin. arXiv preprint, 2019
  10. Generative Adversarial Network for Abstractive Text Summarization Linqing Liu, Yao Lu, Min Yang, Qiang Qu, Jia Zhu. AAAI 2018

* denotes equal contribution.