ZAC Y.C. LIU

About

I’m Zac, currently working on building machine learning (ML) system to detect supply chain disruption at BrainChain AI. I have also been selected as a VC fellow with Laconia Capital.

I previously led R&D and product development, as Head of AI, for an AI delivery and MLOps platform (A360 AI) that abstracts the infrastructure complexity from data scientists, as well as ML team lead for an open source ML platform framework at SylphAI.

I have built, led, managed, and mentored multiple cross-functional teams in data science (DS), ML/ software engineering, and product development, providing technical leadership in generative AI, LLM (Large Language Model), MLOps, data-centric AI, innovative use of DS/ ML from ideation to production at scale, mostly with open-ended projects.

I'm a (hybrid) data scientist + ML engineer; while managing DS/ ML teams, I also do hands-on ML coding, and actively conduct and publish ML research, so I can lead my team with state-of-the-art ML and newest AI trend.

I began my DS career building ML applications to help business become data-driven but my recent work has been focusing on generative AI/ LLM, production ML, and data-centric AI.

I ran an open source project AutoDC (automated data-centric processing) that is complimentary to AutoML (see 2021 NeurIPS DCAI).

I have been serving as an advisor for multiple early stage startups (mostly pre-seed and seed stage), guiding their AI/ ML practices.

I am also holding a research associate position at Stanford University, managing and mentoring for applied ML projects in marina biology, disease ecology, deforestation/ climate change, and remote sensing.

Previously, I built custom ML solutions at Hypergiant, QuantumScape, Driscoll’s, and Monterey Bay Aquarium, in multiple industries, such as commercial space, real-time CRM, solid-state battery manufacturing, supply chain operation, public health, and marine conservation. I also built Kubeflow pipelines on computer vision and NLP components for Google’s AI Hub (now under Vertex AI umbrella).

I have 5+ peer-reviewed applied ML publications and regularly present at top ML conferences (NeurIPS, ICLR, TensorFlow World etc).

My previous research life was in geophysics, earthquake dynamics, and planetary sciences. I built numerical models to simulate ice mountain formation on Saturn's moon Titan and climate patterns inferred from sand dunes on Mars, as well as tsunami propagation caused by mega-earthquakes. My image processing tooling was used to support NASA Cassini Mission, and an improved tsunami simulation code I built has been used to model more tsunami events.

Full CV here; LinkedIn profile.

Timeline

03/2023-now: Founding ML Engineer @ BrainChain AI

05/2023-now: Venture Fellow @ Laconia Capital

11/2017-now: Research Associate (ML) @ Stanford University

01/2023-05/2023: Open Source- ML Lead @ SylphAI

06/2021-03/2023: Head of AI/ Chief Data Scientist @ Andromeda 360 AI | Hypergiant

01/2021-06/2021: Senior ML Engineer/ Senior Software Engineer @ QuantumScape

05/2020-01/2021: Senior Data Scientist @ Hypergiant

06/2019-05/2020: Data Scientist @ Driscoll's

10/2018-06/2019: ML Engineer @ Google (contract via iWorkGlobal)

05/2017-02/2019: Data Scientist @ Monterey Bay Aquarium

08/2013-06/2016: Research Scientist (Data) @ NASA | Smithsonian- joint contractor

08/2010-08/2014: Researcher @ NASA Cassini RADAR Team

Talks

• 08/13/2022- Data Con LA in Los Angeles CA. AutoDC + AutoML = Your AI Dev Superpower. Slides.
• 04/29/2022- ICLR (AI for Earth and Space Science workshop)- online. Improving remote monitoring of carbon stock in tropical forests with machine learning, a case study in Indonesian Borneo.
• 12/14/2021- NeurIPS DCAI (data-centric AI workshop)- online. AutoDC: Automated Data-Centric Processing.
• 08/12/2021- SmallSat Conference- online. Improved Orbital Propagator Integrated with SGP4 and Machine Learning.
• 12/12/2020- NeurIPS Earth Science workshop- online. Keynote: ML and control of parasitic diseases of poverty in tropical and subtropical countries, with a special focus on schistosomiasis. Slides.
• 10/31/2019- O’Reilly TensorFlow World Conference in Santa Clara CA. Building Deep Learning Applications using TensorFlow to Combat Schistosomiasis. Slides.
• 04/10/2019- Invited talk at ML seminar, IBM Silicon Valley Lab, San Jose CA. Building deep learning applications with TensorFlow and Keras: disease ecology, marine biology, and remote sensing. Slides.
• 03/02/2017- Invited talk to Monterey Bay Data Science Meetup at CSU Monterey Bay CA. Data Storytelling: NBA’s 3 point trend, analytics and machine learning. Slides.

Press Coverage

• 03/03/2022- shared thoughts on DeepMind's AlphaCode with Reworked (news article).
• 02/17/2022- research highlights on AutoDC in InsideBIGDATA (news article).
• 10/13/2021- shared thoughts on Natural Language Processing with Lifewire (news article).
• 10/26/2021- applied research on healthcare and climate change featured in Stanford News (news article) and Science Daily (news article).
• 03/05/2020- ML research on Schistosomiasis featured in Stanford Human-centered AI (HAI) spotlights (news article).
• 08/02/2019- ML research on white shark behavior featured in InformationWeek (news article).
• 05/24/2016- geophysics research on Saturn’s moon Titan featured in NASA JPL spotlights (news article).
• 12/01/2015- Mars research featured in UK Research Media (news article).

ML Research

My recent works focus on generative AI, LLM, MLOps and data-centric AI.

I've built an open source data-centric AI tooling, AutoDC (Automated data-centric processing) that aims to automate dataset improvement process. We tested the framework on image data and AutoDC is estimated to reduce roughly 80% of the manual time for data improvement tasks, at the same time, improve the model accuracy by 10-15% with the fixed ML code. We want to expand to NLP and tabular data, open for contributors; check our NeurIPS paper.

Enterprise product development

• A360 AI (team effort): end-to-end ML delivery platform, declarative ML serving (Terraform for ML deployment), SDK
• Active Learning Studio (lead): human-in-the-loop AI, programmatic labeling/ auto-labeling, no-code/ low code
• Efficient AutoML (co-lead): single neural network architecture, based on regularization cocktail (paper), for tabular data

ML pipeline/ Kubeflow component contributions

• BERT preprocessing (Colab)
• TPU ResNet training (Google AI Hub asset)
• ImageNet benchmark: applied data augmentation, TPU, distributed training, 20% more efficient

Applied ML | Data science

I led DS teams to build custom ML solutions and data science use cases to support industry partners and clients as well as academic institutions.

Industry

Domain supported: commercial space, CRM, manufacturing sensory and imagery, supply chain operation, oil and gas, sustainable agriculture.

Academia

Domain supported: remote sensing, marine biology and conservation, disease ecology, deforestation/ climate change, and geophysics/ planetary science.

Peer-reviewed Publications

Applied ML

1. Jerette, J., Liu, Z.Y.-C., Chimote, P., Hastie, T., Fox, E., and Ferretti, F. Shark detection and classification with machine learning. Ecological Informatics (2022), doi: 10.1016/j.ecoinf.2022.101473.
2. Liu, Z.Y.-C., Chamberlain, A.J., Tallam, K., Jones, I.J., Lamore, L.L., Bauer, J. et al. Deep Learning Segmentation of Satellite Imagery Identifies Aquatic Vegetation Associated with Snail Intermediate Hosts of Schistosomiasis in Senegal, Africa. Remote Sensing, SI: Remote Sensing and Infectious Diseases (2022), 10.3390/rs14061345b.
3. Liu, Z.Y.-C., Roychowdhury, S., Tarlow, S., Nair, A., Badhe, S., and Shah, T. AutoDC: Automated data-centric processing. NeurIPS (2021), arXiv:2111.12.
4. Liu, Z.Y.-C., Tarlow, S., Akbar, M., Donnellan, Q., and Senkow, D. Improved orbital propagator integrated with SGP4 and machine learning. SmallSat 2021, paper link.
5. Tallam, K., Liu, Z.Y.-C., Chamberlin, A.J., Jones, I.J., Shome, P., Riveau, G., Ndione, R.A. et al. Identification of Snails and Schistosoma of Medical Importance via Convolutional Neural Networks: A Proof-of-Concept Application for Human Schistosomiasis. Frontiers in Public Health (2021): 900, doi: 10.3389/fpubh.2021.642895.
6. Liu, Z.Y.-C., Moxley, J.H., Kanive, P., Gleiss, A.C., Maughan, M., Bird, L., Jewell, O. et al. Deep learning accurately predicts white shark locomotor activity from depth data. Animal Biotelemetry 7, no. 1 (2019): 1-13, doi: 10.1186/s40317-019-0175-5.

Science

1. Jones, I.J., MacDonald, A.J., Hopkins, S.R., Lund, A.J., Liu, Z.Y.C., Fawzi, N.I., Purba, M.P., Fankhauser, K., Chamberlin, A.J., Nirmala, M. and Blundell, A.G. Improving rural health care reduces illegal logging and conserves carbon in a tropical forest. Proceedings of the National Academy of Sciences (2022), 117(45), pp.28515-28524, doi.org/10.1073/pnas.2009240117.
2. Liu, Z.Y.-C., Radebaugh J., Harris, R., Christiansen, E.H, and Rupper, S. Role of fluids in the tectonic evolution of Titan. Icarus (2016) (SI: Titan's Surface and Atmosphere), 270, 2-13, doi: 10.1016/j.icarus.201_6.02.016.
3. Radebaugh, J., Ventra, D., Lorenz, R.D., Farr, T. Kirk, R.L., Hayes, A., Malaska, M., Birch, S., Liu, Z.Y.-C., Lunine, J., Barnes, J., Le Gall, A., Lopes, R.M.C., Stofan, E., Wall, S., Paillou, P., and Wood, C.A. Alluvial and fluvial fans on Saturn’s moon Titan reveal processes, materials and regional geology. In, Ventra, D. & Clarke, L. E. (eds) Geology and Geomorphology of Alluvial and Fluvial Fans: Terrestrial and Planetary Perspectives. Geological Society, London, Special Publications (2016), 440, doi: 10.1144/SP440.6.
4. Liu, Z.Y.-C., Radebaugh J., Harris, R., Christiansen, E.H, Kirk, R.L., Neish, C.D.,Lorenz, R.D., and the Cassini Radar Team. The tectonics of Titan: Global structural mapping from Cassini radar. Icarus (2016) (SI: Titan's Surface and Atmosphere), 270, 14-29, doi: 10.1016/j.icarus.2015.11.021.
5. Liu, Z.Y.-C. and Zimbelman, J.R. Recent near-surface wind directions inferred from mapping sand ripples on Martian dunes. Icarus (2015), 261, 169-181, doi: 10.1016/j.icarus.2015.08.022.
6. Liu, Z.Y.-C. and Hargitai H. Mountain (Titan). (2014) In: A. Kereszturi and H. Hargitai (Eds), Encyclopedia of Planetary Landforms, Springer-Verlag Berlin Heidelberg, Germany, doi: 10.1007/978-1-4614-9213-9_508-1.
7. Liu, Z.Y.-C. and Harris, R. Discovery of Possible Mega-Thrust Earthquake along the Seram Trough from Records of 1629 Tsunami in Eastern Indonesian Region. Natural Hazards (2013) (SI: Extreme Geohazards), 72(3), 1311-1328, doi: 10.1007/s11069-013-0597-y.

Get In Touch

I’m best reached via email (zacqoo at gmail dot com) and open to interesting collaboration.

• Twitter
• GitHub

Contact

• Twitter
• Facebook
• Instagram
• GitHub

Elements

i = 0;

while (!deck.isInOrder()) {
    print 'Iteration ' + i;
    deck.shuffle();
    i++;
}

print 'It took ' + i + ' iterations to sort the deck.';