Skip to content
Sophie Yin

About

Seattle, WA
Sophie Yin

bio

Now

I'm a machine learning engineer who builds production ML and agentic AI systems — the kind that price real assets, answer real customers, and page someone when they break. For the last few years that has meant owning pricing end to end at Alt: models, infrastructure, tooling, and the agents that sit on top.

I started in data science across banks and insurers — HSBC's R&D lab, RBC, CI, Sun Life — doing churn models, credit risk, synthetic data, and experiment design. What pulled me toward engineering was watching good models die in handoff: a model is not a prediction so much as a promise someone has to keep, and keeping it means owning the system around it.

Outside work I mentor career-changers into analytics and data science. Most of my side projects are agents I built because I needed them: for the content I make, the marketing around it, and my own investing. Being a tool's only user is the fastest way to learn where it breaks.

experience

Since 2019
  • 2022 — Present

    Senior Machine Learning Engineer · Alt

    • Sole engineering owner of pricing for 9+ months across four product surfaces — roadmap, architecture, on-call, and stakeholder alignment as a one-person team.
    • Built the agentic selling product that more than doubled offer acceptance in its first phase (11.5% → 26%), and the auto-pricing triage that raised the auto-priced rate by more than 20% (patent pending, named inventor).
    • Rebuilt the expert-pricing tool on a secure, auditable architecture — 2× processing speed, ~4× quote throughput at rollout.

    Case studiesagentic sellingauto-pricing triageevent-driven agent backboneML platform optimization

  • 2020 — 2022

    Full-Stack Data Scientist · HSBC, R&D Lab

    • Prototyped a conditional GAN for synthetic transaction data under regulatory and privacy constraints.
    • Shipped a Python + Scala graph builder and EDA tool used across all projects — cut ETL and exploration time on payments data by 25%.
    • Led the Canada Innovations branch-analytics project — surfaced 200+ inside-sales opportunities.
  • 2019 — 2020

    Data science · RBC · CI Global Asset Management · Sun Life

    • RBC: transaction-level churn modeling with Cox survival analysis, turned into risk scores advisors used to retain clients.
    • CI: fixed leakage, class imbalance, and overfitting in purchase and redemption prediction.
    • Sun Life: an A/B testing framework with non-compliance corrections.

mentorship

  • 2023 — 2026

    Mentor — Data Analytics · CareerFoundry

    • Mentored career-changers through the Data Analytics program — project reviews, mock interviews, and coaching on data-driven thinking.

education

  • 2018 — 2020Master of Economics · University of Waterloo
  • 2014 — 2018Bachelors of Mathematical Economics · University of Waterloo

toolbox

  • ModelingClassification and regression · Deep learning (PyTorch) · Survival and uplift models · Causal inference · Interpretability (SHAP)
  • AI systemsLLM agents and orchestration · LLM-as-judge evals · Hybrid ML + LLM pipelines · Tracing (Langfuse)
  • TestingA/B testing · MLflow · Monitoring and drift detection
  • Data & infraPython · SQL · Spark · Snowflake · Airflow · Postgres · AWS (SQS, Lambda) · Docker · Terraform · Datadog