# William F. > Software Engineer | Responsible AI Researcher | Looking for Doctoral Research Fellow, Data Scientist Roles Location: Boston, Massachusetts, United States Profile: https://flows.cv/williamf1 My primary research spans private data analysis (differential privacy, machine unlearning). More recently, I am interested in private synthetic data generation. Technically, I am specifically interested and skilled in Machine Learning, Computer Vision, and Natural Language Processing. I am also an experienced Python, C++, JavaScript (React), TypeScript (Angular) programmer, concentrating on Server-side core algorithm R&D. I am also an AWS Certified Solutions Architect (Associate). ## Work Experience ### Software Engineer II (R&D — Differential Privacy, Synthetic Data, LLMs) @ Capital One Jan 2025 – Present Applied Research • Differential Privacy • Synthetic Data • Large Language Models ### Software Engineer II @ Capital One Jan 2025 – Jan 2025 • Designed and deployed production Flask REST APIs on AWS Fargate behind an Application Load Balancer and Route 53 CNAME. • Built an event-driven ETL pipeline — S3 ➔ SNS ➔ SQS ➔ Lambda ➔ Snowflake — ingesting ≈ 17 GB/month of compliance files with exactly-once semantics via idempotent S3 object-tag checks. • Designed and automated regional fail-over for the entire stack (S3 ➔ SNS, Fargate BFF API, EventBridge + Batch, OpenSearch), authoring 4 runbooks and 2 Python scripts with unit/e2e tests; cut recovery time from 40 min to < 5 min. • Led a feature-flag A/B experiment (Segment) on two UI variants across 100 M users; Snowflake analysis showed ~125 % click-through for Variant B, guiding product-pilot rollout. • Automated operational alerts with CloudWatch metric filters and SNS ➔ PagerDuty hooks that trigger on any HTTP 5xx in a 5-minute window and for OpenSearch CPU/Mem thresholds. • Hardened security & compliance: provisioned least-privilege IAM roles and KMS-encrypted S3 buckets / SQS queues; passed 2024 audit with zero critical findings. • Mentored six engineers on AWS best practices and code reviews; 6 out of 6 have acquired the AWS SAA certificate. ### Software Engineer I @ Capital One Jan 2024 – Jan 2025 Full-Stack Developer for [Redacted] • Developed a proprietary tool using machine learning to predict B2B credit card acceptance and support bank relationship managers to develop stickier relationships with small businesses. • This innovation contributed directly to over ~$3+ billion in quarterly expenditures. Tech Lead for [Redacted] • Led a machine learning project to forecast delinquency risks in business accounts and devise strategies to minimize overcharges. • Oversaw workflow, including model development, monitoring, and performance evaluation. ### Researcher @ Boston University Graduate School of Arts & Sciences Jan 2023 – Present 1. Oral and poster @ International Conference on Algorithmic Learning Theory (ALT 2026): Privately Learning Decision Lists and a Differentially Private Winnow Preliminary version: Poster @ TPDP (Theory and Practice of Differential Privacy) 2025: Differentially Private Winnow for Learning Halfspaces and Decision Lists • We give new differentially private learning algorithms for halfspaces and decision lists in the online and PAC models. In the online model, we give a private analog of the classic Winnow algorithm for learning large-margin halfspaces. As an application, we describe how to privately learn decision lists in the online model, qualitatively matching state-of-the art non-private guarantees. We also give a learner for decision lists in the PAC model, where we give a computationally efficient algorithm with similar sample complexity as the best non-private algorithms. 2. Algorithm design for differentially private query release of nonconvex structures. ### Research Assistant @ Boston University Graduate School of Arts & Sciences Jan 2021 – Jan 2023 Privacy-Preserving Machine Learning • Algorithm development and theoretical analysis of differentially private (DP) learners in the batch (PAC) and online settings for polynomial learnable concept classes (i.e. generalized decision lists, sparse disjunctions, halfspaces, etc.) Contributions • PAC setting: Developed a novel DP and computationally efficient algorithm for generalized decision lists with optimal sample complexity • Online setting (oblivious adversaries): Identified adaptation of DP algorithm for expert prediction that learns k-width disjunctions. • Online setting (oblivious adversaries): Developed a variation of the Winnow algorithm that learns k-width disjunctions with high probability regret bound O(klog(d)). Identified two other variants with optimal regret. • Advisor: Mark Bun • Collaborators: None ### Research Assistant @ Boston University College of Engineering Jan 2023 – Jan 2024 Responsible & Safe AI • Algorithm development and empirical analysis of unlearning methods for computer vision tasks. • Experimented with other unlearning methods (i.e. SCalable Remembering and Unlearning unBound (SCRUB), teacher-student, negative gradient descent, and variants with relative entropy regularization) on CIFAR-10. • Graphical Models (on pause) Contributions • Developed a dual-objective approximate machine unlearning algorithm for Image classification (Top 3% of NeurIPS 2023 Machine Unlearning Challenge). • Advisor: Wenchao Li • Collaborators: C. Yu ### Software Engineer Intern @ Capital One Jan 2023 – Jan 2023 Card Technology Solutions • Re-architected a legacy Java/Spring Boot “dynamic purchasing power” API (ECS) into a Python-based AWS Lambda service; cut package size and eliminated ECS cluster costs. • Reduced monthly compute + maintenance spend while supporting credit-card limits for 15 M up-market & SMB customers. ### Software Engineer Intern @ Hewlett Packard Enterprise Jan 2022 – Jan 2022 | Boston, Massachusetts, United States High-Performance Computing (HPC) Solutions • Developed automation software to execute test suites on nightly builds for HPE Performance Cluster Manager (HPCM). • Led the development of a sophisticated monitoring solution for HPCM that tracks test environments, orchestrates the interplay between Ansible playbooks and test suites, and meticulously logs every request and execution. ### Computer Science Grader @ Boston University Jan 2021 – Jan 2021 • Graded assignments weekly for over 80 students in an upper-level computer science class on Automata and Formal Language Theory, Computability Theory, Reductions, and Complexity Theory. ### Software Engineer Intern @ Leopard Imaging Inc. Jan 2021 – Jan 2021 | Fremont, California, United States Embedded Camera Solutions • Prototyped real-time mask-detection system using YOLOv5 on AWS EC2 GPU; processed 30 FPS video streams. • Delivered a Streamlit dashboard + PostgreSQL backend for live compliance reporting across a pilot facility. ### Research Intern @ Harvard Medical School - Massachusetts General Hospital Jan 2018 – Jan 2018 Wu Laboratory at Harvard Cutaneous Biology Research Center • Genome modification for Escherichia Coli ### Research Intern @ BrainCo Inc Jan 2017 – Jan 2017 | Somerville, Massachusetts, United States Harvard Innovation Lab Brain Machine Interface Solutions • Analysis of Neurofeedback, Ritalin, and other ADHD treatment ### Human Resources Intern @ Cigna Jan 2017 – Jan 2017 | Shanghai, China Full-time ## Education ### Bachelor of Arts - BA in Computer Science Boston University ### Bachelor of Arts - BA in Mathematics (Pure and Applied) Boston University ### Master of Science - MS in Computer Science Boston University ## Contact & Social - LinkedIn: https://linkedin.com/in/william-f-a563381b2 - Portfolio: http://www.williamfangtech.com/ --- Source: https://flows.cv/williamf1 JSON Resume: https://flows.cv/williamf1/resume.json Last updated: 2026-03-28