David Pissarra
Doctoral Researcher at New York University
New York, New York, United States
Summary
🤩
Rockstar🎓
Top SchoolDavid Pissarra is a PhD student in Computer Science at NYU Courant and an Applied Scientist Intern at AWS with four years of hands-on ML research and engineering experience. He has blended academic rigor from NYU, Tsinghua and Técnico Lisboa with practical research roles at Fraunhofer, CMU, and industry internships, focusing on model deployment and quantization. An active open-source contributor, he extended mlc-llm to support many modern code and chat models and implemented q8f32 quantization workstreams to make large models more efficient. Comfortable bridging research and production, he teaches and mentors while pushing model-compatibility and performance improvements that aren’t always visible in papers. Based in New York, he brings a cross-cultural education and a track record of shipping integrations that enable wider LLM adoption.
4 years of coding experience
1 year of employment as a software developer
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at New York UniversityMaster of Science Advanced Computing, Master of Science Advanced Computing at Tsinghua UniversityMaster of Science Computer Science and Engineering, Master of Science Computer Science and Engineering at Instituto Superior Técnico
Github Skills (11)
quantization10
tvm10
custom-configuration10
configurations10
language-model10
system-configuration10
yml-configuration10
compilation10
python10
compile10
llm10
Programming languages (4)
Github contributions (5)
mlc-ai/mlc-llm
May 2023 - Oct 2024
Universal LLM Deployment Engine with ML Compilation
Role in this project:
ML Engineer
ML EngineerContributions:26 reviews, 35 PRs, 8 pushes in 1 year 4 months
Contributions summary:David made several contributions to the model support within the repository, specifically adding and updating code for integrating new models like StarCoder, WizardCoder, ChatGLM2, CodeGeeX2, and CodeLlama. These changes included modifications to existing Python scripts and documentation to enable compatibility and address related model-specific configurations. Furthermore, the user added and updated model configurations and templates to support different architectures. The user also worked on the implementation of quantization techniques, adding support for q8f32 quantization.
language-modelllmmachine-learning-compilationtvm
davidpissarra/mlc-llm
Jun 2023 - Jul 2024
Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
Contributions:218 pushes, 37 branches in 1 year 1 month
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.