Richard Chiou

Lead AI/ML Engineer

Outlier

Jan 2024 - Current (2 years 7 months)

• Fine-tuned computer vision and CNN models (ResNet-50) using PyTorch to identify species, individual animals, sex, and age-class from wildlife footprint images, achieving over 95% accuracy. • Integrated optimized ONNX models into WildTrackAI mobile app, reducing prediction time from 2s to 300ms, improving accessibility for 1000+ field users. • Deployed a BioBERT-based LLM model using LangChain-powered RAG on SageMaker to handle 500+ patient conversations per month, providing personalized healthcare advice. • Improved clinical workflow efficiency, reducing average doctor-patient meeting time by 30% by pre-summarizing patient information from virtual assistant conversations using a BART-based Transformer model. • Led a cross-functional AI te

Senior AI/ML Engineer

StreetLight Data

Jan 2022 - Dec 2023 (2 years)

• Architected spatio-temporal forecasting models using Graph WaveNet and LangGraph to predict traffic flow one hour ahead, achieving 23% higher accuracy compared to ARIMA. • Applied Transformer-based temporal encoders for multi-horizon congestion prediction across heterogeneous inputs, enabling early detection of evacuation bottlenecks and reducing congestion prediction error by 18%. • Created real-time incident detection models combining loop detector data, GPS traces, and DOT event feeds to classify crashes and stalled vehicles with 91% precision and 87% recall, reducing operator detection latency by 35%. • Built a reinforcement learning model for adaptive traffic signal timing and contraflow recommendations, validated in SUMO simulations

Data Scientist, Instructor

Metis

Aug 2019 - Dec 2021 (2 years 5 months)

• A Mentored learners in feature engineering, model evaluation, and deployment, resulting in measurable skill improvements and career placements for 70+ students in data science roles. • Authored 50+ hands-on exercises and guided 20+ capstone projects, producing production-ready ML models and analytics solutions.

AI/ML Engineer

Signifyd

Aug 2018 - Jul 2019 (1 year)

• Engineered machine learning models to detect fraudulent e-commerce transactions, processing 100K+ daily transactions and reducing chargebacks by 15%. • Optimized adaptive fraud thresholds and conducted A/B tests, improving legitimate transaction approval rates by 10% while maintaining high fraud detection accuracy.

B

Senior Data Scientist

Brain Technologies

Jul 2017 - Jul 2018 (1 year 1 month)

• Formulated data generation guidelines and managed data generation workflows, creating and annotating 50,000+ examples to support the NLP team and ensure high- quality training data. • Operationalized general and domain-specific entity recognition systems using spaCy and SENNA, improving the virtual assistant's entity extraction accuracy by 25%.

x

Mid-level Data Scientist

xAd

Aug 2016 - Jun 2017 (11 months)

• Executed a patent-pending statistical algorithm using hierarchical and Bayesian modeling on 10M observations to improve ad campaign-driven store visits by 25%. • Developed a model to rank mobile user id quality leveraging 30+ behavioral and demographic features, increasing targeting precision by 20% across campaigns.

Mobile Tools Development Intern

PayPal

Aug 2014 - Apr 2015 (9 months)

• Constructed the PPUtils tool using QIJaws API to automate the creation of 10K+ test user accounts, supporting continuous integration for PayPal iOS and Android apps. • Performed root cause analysis on Android test failures and built a login performance dashboard with automated alerts, improving testing efficiency by 45%.

About

Detail

Timeline

Résumé