Jiaqi Gan
I build, train and evaluate machine learning systems, from small language model post-training to interpretable models of single-cell dynamics.
Physics Ph.D. candidate at the University of Pittsburgh (expected April 2027) and ML research intern at ScamAI.
Open to ML Research Engineer, Machine Learning Engineer and Applied Scientist roles.
Selected work
All research- Small LM Post-Training for AI Call Agents Synthetic training data and one LoRA recipe for six small LMs that answer calls.
- CallScreenBench A benchmark for small LMs that answer calls on their owner's behalf.
- GraphVelo Open-source package for multimodal single-cell velocity.
- LogicDynamo Interpretable ODE models of how cells change state.