Andrey Kan
Senior Staff Data Scientist
Queensland, Australia
Summary
👤
Senior🎓
Top SchoolAndrey Kan is a Senior Staff Data Scientist with 12 years' experience at the intersection of machine learning, graph mining and computational biology, now based in Queensland, Australia. He has driven GenAI and production ML systems at Amazon—shipping features like SageMaker JumpStart fine-tuning, deployment defect monitoring, and business-facing apps—and now leads data science at Commonwealth Bank. Andrey blends research rigor (PhD in Computer Science) with hands-on engineering in Python, Spark and AWS, and has practical expertise in graph neural networks and spatiotemporal data mining. His open-source work includes fine-tuning and demonstrating Hugging Face text2text models within Amazon SageMaker, applying parameter-efficient methods like LoRA to real-world deployments. Colleagues value him for turning research problems into production-ready evaluation frameworks and robust system designs that bridge product, engineering and science.
12 years of coding experience
17 years of employment as a software developer
BS Telecommunications, BS Telecommunications at Tashkent University of Information TechnologiesThe University of MelbourneLomonosov Moscow State University
Github Skills (19)
python10
machine-learning10
sagemaker10
huggingface-transformers10
fine-tuning10
jupyter-notebook10
nlp10
aws9
mlops9
deep-learning8
mle8
inference8
ml8
text-generation8
data-science7
Programming languages (1)
Github contributions (5)
aws/amazon-sagemaker-examples
Apr 2023 - Jun 2023
Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.
Role in this project:
ML Engineer
ML EngineerContributions:13 reviews, 7 PRs, 13 comments in 2 months
Contributions summary:Andrey primarily contributed to fine-tuning and demonstrating the use of Hugging Face text2text models within the Amazon SageMaker environment. Their work involved fine-tuning models like FLAN T5 on new tasks, integrating the models for text generation and question answering, and configuring inference endpoints. They also focused on setting environment variables for optimized model server configurations. The user demonstrated expertise in utilizing SageMaker JumpStart for pre-trained model deployment and applying parameter-efficient fine-tuning approaches like LoRA.
pythonjupyter-notebooktrainingawssagemaker
malysch/amazon-sagemaker-examples
Apr 2023 - Jun 2023
Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.
Contributions:2 PRs, 53 pushes, 9 branches in 2 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.