# Ezzeri Esa > Software Engineer, AI / ML | ex-Square, Airtable Location: San Francisco, California, United States Profile: https://flows.cv/ezzeri I’m a software engineer with experience in ML (payments and lending) and data infra (production and data warehouse). I’ve built end-to-end ML workflows (feature store, model training and inference) and optimized data pipelines that process petabytes of data. I’ve attended Recurse Center twice and contributed to open source. My recent focus has been on building people skills. In previous interview cycles, I was interested in back-end, ML and data engineering roles (or roles where I can combine these), with a tight-knit team moving in synchrony. My manager at a previous role described me as “particularly strong at distilling complex, disorganized information and repackaging it into a beginner-friendly format”. https://ezzeriesa.notion.site https://github.com/savarin ## Work Experience ### Founding Engineer @ Stealth Jan 2024 – Present ### AI Engineer @ Hex Jan 2024 – Jan 2024 | San Francisco Bay Area • Rebuilt evals framework from local to remote execution to minimize production drift, enabling iteration with confidence across ~1,500 SQL, Python and chart evals • Developed RAG and embedding techniques for notebook search, significantly improving search accuracy to enable deflection of inbound user queries to existing notebooks ### Software Engineer, Machine Learning @ Step Jan 2023 – Jan 2024 | San Francisco Bay Area • Reduced agent caseload for card fraud by 40%, by improving the workflow from running a single XGBoost model in real-time to multiple models in real-time and in batch • Migrated ACH and check fraud workfows from a rule-based to a model-based system, implementing the GCP components end-to-end – feature store, model training and inference ### Participant @ Recurse Center Jan 2023 – Jan 2023 • Self-taught various topics of interest: functional programming (Haskell, Prolog, Idris), generative models ### Software Engineer, Data Infra @ Airtable Jan 2020 – Jan 2022 | San Francisco Bay Area • Led task force to streamline production MySQL to S3 to Redshift pipeline, reducing end-to-end time from 16 to 8 hours with incremental loads and parallelized runs • Migrated SQL runner framework from local to remote execution with Github Actions, AWS Codebuild and Terraform, in addition to reducing Docker image build times by 60% • Developed SQL testing framework by standardizing interfaces and use of SQLAlchemy interactions; minimizing boilerplate with functional programming and code generation • Coordinated incident response to system-wide errors, and recovered data loss with heuristics developed from analysis of historical patterns ### Software Engineer, Back-End @ Theorem LP Jan 2019 – Jan 2020 | San Francisco Bay Area • Developed a Jupyter notebook workflow for data scientists that streamlines sharing notebooks, scheduling Argo jobs, and managing dependencies via Bazel • Created Theorem's 'source of truth' – a set of ETLs/tables in Redshift that standardize loan data, powering use cases across finance, operations and data science • Collaborated with investor relations to create monthly snapshots of fund performance for investors, and with finance to automate reconciliation of external sources with internal financial models • Wrote documentation for company-wide knowledge share: mechanics of leverage facilities, calculating default/prepay probabilities, deploying with Kubernetes ### ML Engineer / Data Scientist, Risk @ Square Jan 2015 – Jan 2019 | San Francisco Bay Area • Developed fraud detection algorithms and machine learning models to protect Square and its customers from financial loss and reputational damage • Drove end-to-end cross-functional analytics projects: build experimental framework and hypotheses, collect and analyze data, present key insights in support of decision making • Reduced fraud loss on online products by 50% ($400k/month) via model selection and feature engineering • Built domain expertise to optimize Disputes (by improving seller experience and dispute win probability) and Recovery (by maximizing funds recovered from chargebacks) • Led Python classes on machine learning and neural networks for ~20 employees every quarter ## Education ### B.A. (Hons) / M. Math. in Mathematics University of Cambridge ### Special Student / Teaching Fellow Harvard University ### Cuisine de Base Le Cordon Bleu Paris ### B.A. (Hons) in Law University of Cambridge ## Contact & Social - LinkedIn: https://linkedin.com/in/ezzeriesa - Portfolio: https://ezzeriesa.notion.site - GitHub: https://github.com/savarin --- Source: https://flows.cv/ezzeri JSON Resume: https://flows.cv/ezzeri/resume.json Last updated: 2026-04-11