Open to opportunities

chengfu User

@chengfuuser

Message

Senior data scientist specializing in on-chain risk models, ML systems, and scalable data engineering.

Canada

Message

What I'm looking for

I seek a role building production ML and data platforms that drive measurable risk reduction and product decisions, with collaborative teams and strong engineering practices.

I am a Senior Data Scientist with deep experience building production ML systems and real-time risk platforms for Web3 and financial applications. I combine econometrics, machine learning, and software engineering to deliver robust, data-driven products.

At Kraken I designed on-chain risk models, anomaly detection systems, and asset health scoring using Random Forest, XGBoost, GARCH, and VAR models. I built ETL and pipeline solutions with Airflow, AWS Lambda, and scalable ingestion from blockchain nodes and APIs.

Earlier, at Amazon I developed computer vision and sequence models deployed on AWS SageMaker, and processed large-scale datasets with PySpark and EMR. I have taught databases and econometrics, supporting students in SQL, NoSQL, Python, and R.

I prioritize measurable impact, production reliability, and cross-functional collaboration to reduce false positives, improve onboarding decisions, and automate risk alerts—bringing statistical rigor and engineering discipline to high-stakes data problems.

Experience

Work history, roles, and key accomplishments

Current

Senior Data Scientist

Current

Kraken Exchange

Jul 2022 - Present (3 years 3 months)

Developed a real-time on-chain risk assessment platform and asset listing health model using machine learning, reducing AML false positives by 25% and enabling data-driven asset onboarding decisions.

Python SQL Random Forest XGBoost Apache Airflow AWS Lambda Clustering GraphQL

Applied Science Intern

Amazon

Dec 2021 - Jun 2022 (6 months)

Built and deployed computer vision models for mouse/cursor tracking on SageMaker, using CNNs and LSTMs to improve customer behavior prediction and real-time inference latency.

Computer Vision CNN TensorFlow Keras Pyspark AWS Sagemaker Data Processing

Teaching Assistant

University of British Columbia

Nov 2020 - Nov 2021 (1 year)

Assisted courses in Databases in Data Science and Introduction to Econometrics II by guiding students in SQL/NoSQL, data modeling, regression diagnostics, and statistical inference using Python and R.

SQL NoSQL Data Modeling Python R Econometrics Query Optimization Teaching

Education

Degrees, certifications, and relevant coursework

University of British Columbia

Honours Bachelor of Science, Econometrics and Computer Science

Activities and societies: Teaching assistant for CPSC 368 (Databases in Data Science) and ECON 326 (Introduction to Econometrics II).

Honours Bachelor of Science in Econometrics and Computer Science with coursework in advanced econometrics, machine learning, databases, algorithms, and statistical inference.