Jian Shen
CA
Summary
👤
SeniorJian Shen is a founding deep learning engineer with eight years of experience building production-grade ML systems at the intersection of LLMs, multimodal models, and generative AI for real-world applications. He led R&D efforts from 3D computer vision for LiDAR at Velodyne to transformer- and diffusion-based models for drug generation, including training a Llama3-based drug-generation model and guiding models that influenced actual drug production. As founder/tech lead at SAGI he architected multi-agent LLM + RAG systems delivering PhD-level QA performance with a 32B model and built multimodal treatment-suggestion pipelines using DPO. His background in inorganic chemistry and hands-on research roles gives him a rare blend of domain science intuition and deep engineering rigor. Based in Albany, NY, Jian is self-taught in ML, resiliently transitioning from chemistry to leading applied AI projects that span academia, startups, and industry. He’s particularly adept at turning advanced research ideas into deployable systems that impact decision-making in high-stakes domains.
8 years of coding experience
Github Skills (56)
attention-mechanism9
streamlit8
chatbot8
alfred-workflow8
neovim-plugin8
embedding8
pdf-viewer8
vim-plugin8
chatgpt7
transformers7
epub7
artificial-intelligence7
pdf7
retrieval-augmented-generation7
proxy7
Programming languages (6)
Github contributions (5)
TimS-ml/My-ML
Jan 2021 - Dec 2022
Contributions:9 commits, 96 pushes, 3 branches in 2 years
TimS-ml/llama_index
Mar 2024 - Oct 2024
LlamaIndex is a data framework for your LLM applications
Contributions:20 pushes in 7 months
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.