Skip to content

diego@stanford:~$ whoami

Diego Sanchez

edu: Stanford University — B.S. Computer Science (AI) & Statistics · Class of 2028

now: Research Engineer Intern @ Coinbase, ML Platform

focus: ML systems · Bayesian optimization · adaptive experimentation

prev: Microsoft (M365 Copilot Search NLP) · Stanford Medicine (LLM research)

$ request_resume$ view_projects$ github$ linkedin

resume available on request — opens your email app

Diego Sanchez

diego@stanford:~$ cat ./about.md

About

I'm a CS and Statistics student at Stanford. Last summer I was at Microsoft working on the NLP systems behind M365 Copilot Search, and before that I built the LLM backend for a patient-flow research project at Stanford Medicine. This summer I'll be at Coinbase on the AI/ML Platform team.

The through-line: I like taking ML ideas and turning them into systems people actually use — backends, pipelines, and the infrastructure around models.

$ which -a

PythonC++C#TypeScriptFastAPIPyTorchLangChainDockerSQLAzure ML

diego@stanford:~$ ls ./experience

Experience

Coinbase logo

Research Engineer Intern, ML Platform

Coinbase · Jun 2026 – Present · San Francisco, CA

focus: ML model rollout promotion as sequential decision-making under uncertainty

impact:

  • -Replacing a fixed, manually gated traffic-ramp schedule with an adaptive Bayesian optimization policy for ML model rollout promotion.
PythonBayesian OptimizationGaussian ProcessesML Platform
Microsoft logo

Software Engineering Intern, M365 Copilot Search NLP

Microsoft · Jun 2025 – Sep 2025 · Redmond, WA

97% recall · 92% precision~$430k → ~$4.2k/yr

focus: LLM-based DSAT triage, NLP systems, backend automation

impact:

  • -Built an LLM-powered triage pipeline for Copilot Search feedback with 97% recall / 92% precision on 1k+ queries and 99%+ PII removal across 50k logs.
C#PythonAzure MLLLMsNLP
SURF Stanford Medicine logo

LLM Developer Research Assistant

SURF Stanford Medicine · Jan 2025 – Jun 2025 · Stanford, CA

95% LLM output accuracy

focus: HIPAA-compliant LLM backend, healthcare analytics, model evaluation

impact:

  • -Built HIPAA-compliant FastAPI backend and LLM for real-time unit analytics and predictive forecasting.
PythonFastAPILangChainSQLDocker
Anthropic logo

Claude Ambassador Builder

Anthropic · Jan 2026 – Present

focus: AI developer tools, community demos, agent workflows

impact:

  • -Selected as Claude Ambassador Builder to advance AI-powered development tools.
LLMsPythonDeveloper Tools
Jane Street logo

UNBOXED Fellow

Jane Street · Jul 2024 – Aug 2024

focus: Quantitative systems, SQLite, strategy analysis

impact:

  • -Selected for a 3-week quantitative trading program focusing on stats and game theory.
PythonSQLiteStatistics

$ cat ./education

Stanford University logo

Stanford University — B.S. Computer Science (AI Track) & Statistics · Class of 2028

coursework: Data Structures & Algorithms, Computer Organization & Systems, Probability, Linear Algebra

clubs: Stanford Computer Forum, SOLE, ACM, Stanford AI Club

diego@stanford:~$ ls ./projects

Projects

InferScale

ML PlatformBackendAI Systems

description: FastAPI inference microservices with Docker Compose, multi-mode routing, benchmarking harness, and C++17 deterministic replay.

highlights:

  • -Built FastAPI inference microservices with Docker Compose for scalable model serving.
  • -Implemented routing for speculative and disaggregated prefill/decode modes with benchmarking harness.
  • -Added C++17 deterministic replay on traces for reproducible performance analysis.

stack:

PythonFastAPIPyTorchDocker ComposePrometheusC++17
links:
[GitHub]

Hospital LLM

Healthcare AINLP SystemsBackend

description: HIPAA-conscious LLM backend for querying hospital operations data through schema-aware tools.

highlights:

  • -Built tool-calling backend for structured hospital data queries with schema grounding.
  • -Added guardrails for safer healthcare deployment and reliability checks.
  • -Created evaluation strategy for model accuracy and consistency on clinical operations data.

stack:

PythonLangChainDockerSQLFastAPI
links:
[GitHub]

BUICU

Research EngineeringHealthcare AI

description: Bayesian ICU forecasting model using conjugate inference with an interactive Streamlit interface.

highlights:

  • -Built Bayesian forecasting pipeline for ICU patient outcomes with conjugate inference.
  • -Implemented Monte Carlo simulation for uncertainty quantification.
  • -Deployed interactive Streamlit dashboard for clinical analytics exploration.

stack:

PythonNumPySciPyStreamlitBayesian Inference
links:
[GitHub]

$ ls ./projects --all

StudyBuddyConnect

Platform connecting students for collaborative learning and study session coordination.

[GitHub]

HeadStart

Project management and productivity tool for teams and individuals tracking goals.

[GitHub]

Trade Bot

Automated trading bot with algorithmic strategies, risk management, and performance analytics.

[GitHub]

Chromatic Tuner

Web-based chromatic instrument tuner with real-time audio processing and visual feedback.

[GitHub]
$ view_all_on_github

diego@stanford:~$ contact

Contact

new_message

diego@stanford:~$ mail dsanh14@stanford.edu

email: dsanh14@stanford.edu

Opens in your mail app — or copy the address above.

githublinkedinresume (request by email)