Cristian聽Challu
Analyst at Nixtla
United States
Summary
馃ぉ
Rockstar馃帗
Top SchoolCristian Challu is a Machine Learning PhD candidate at Carnegie Mellon University and an analyst at CMU Auton Lab with eight years of experience applying deep learning to time-series anomaly detection and forecasting. He co-founded Nixtla and contributes to its neuralforecast library, focusing on scalable neural forecasting and hyperparameter-driven model optimization. Previously an AI research scientist at Amazon, his work on multivariate time-series earned publications at AISTATS and ICLR, bridging academic rigor with production-minded ML engineering. With a strong quantitative foundation (BS in Applied Mathematics, BA in Economics, MS in Data Science) and hands-on back-end experience, he excels at turning research ideas into reliable code and deployable models. Unusually for an academic, he pairs entrepreneurship with practical tooling contributions to open-source forecasting infrastructure.
8 years of coding experience
6 years of employment as a software developer
Bachelor of Science - BS, Applied Mathematics, Bachelor of Science - BS, Applied Mathematics at Instituto Tecnol贸gico Aut贸nomo de M茅xicoDoctor of Philosophy - PhD, Machine Learning, Doctor of Philosophy - PhD, Machine Learning at Carnegie Mellon University
Github Skills (21)
m410
pytorch10
system-configuration10
python10
pandas10
machine-learning10
time-series10
numpy10
forecasting10
custom-configuration10
deep-learning10
m4a10
hyperparameter-tuning10
forecast10
configurations10
Programming languages (2)
Github contributions (5)
Nixtla/neuralforecast
Apr 2021 - Jan 2023
Scalable and user friendly neural :brain: forecasting algorithms.
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:1 release, 181 reviews, 62 commits in 1 year 9 months
Contributions summary:Cristian primarily focused on modifying hyperparameter configurations within a script for `nbeats_x_i`, a neural forecasting model. The changes involved adjusting parameters related to the model architecture and optimization, like input_size_multiplier, n_hidden, activation functions, learning rate and loss. They also introduced and modified settings specifically for the model. This suggests a focus on experimentation and optimization of neural forecasting models within the `neuralforecast` project, indicating back-end development with an ML engineering focus.
forecastingbrainnbeatsxtime-seriesnhits
autonlab/esrnn
Jan 2020 - May 2021
Hybrid ES-RNN models for time series forecasting
Contributions:9 commits, 1 PR, 1 push in 1 year 4 months
pytorchforecastingrnndeep-learningseries-forecasting
Find and Hire Top DevelopersWe鈥檝e 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.