# Linli Wang

> SDE @ AWS Agentic AI | LLM Systems & Infrastructure

Location: San Francisco Bay Area, United States
Profile: https://flows.cv/linli

I’m a software engineer at Amazon (AWS) working on production-grade agentic AI systems for infrastructure modernization.

My work focuses on designing LLM-driven orchestration systems, including agent workflows, schema-validated outputs, and developer-facing tools that help large, legacy workloads migrate onto AWS with greater automation, safety, and clarity.

I enjoy tackling ambiguous, high-leverage problems and turning them into clear system designs—defining boundaries, abstractions, and tradeoffs that can be reliably implemented, evaluated, and shipped. I’ve also led the design and delivery of a stretch initiative to modernize IaC execution, translating early-stage architectural ideas into a working production system.

Outside of my day-to-day engineering work, I host Aesthetic Intelligence Circle (AIC), a small, curated salon series in the Bay Area that brings together engineers, artists, founders, and researchers to explore judgment, taste, and how emerging technologies shape creative decision-making.

I’m especially interested in AI infrastructure, agentic systems, and decision-oriented interfaces, and in building tools and communities that support thoughtful creation.

Always happy to connect with people building in these areas.

## Work Experience
### Software Engineer @ Amazon
Jan 2024 – Present | Santa Clara County, CA
• Owned the end-to-end design and implementation of an LLM-powered IaC Subagent within a centralized Orchestrator, automating CloudFormation analysis and transformation for large-scale production modernization workflows.
• Established the subagent as a shared platform capability adopted by 3 internal services, supporting Beta, Gamma, and Production environments with execution isolation and standardized contracts.
• Designed agent interfaces and artifact schemas enabling safe downstream consumption by EBA and DBMod, achieving ~96% validated output acceptance across 100+ recurring production runs weekly.
• Built the EBA operational dashboard from scratch, centralizing agent execution status and artifacts, and saving ~7–8 hours per on-call week by eliminating manual cross-account inspection.
• Led early-stage design and POC work for a P0 Pipeline Transformation, owning a pipeline-centric architecture and driving complex execution trade-offs across build, deploy, and agent-based workflows.

### Machine Learning Engineer @ DiDi
Jan 2024 – Jan 2024
• Developed and trained Python-based uplift modeling pipelines for targeted coupon distribution, applied at scale across millions of registered users and contributing to a ~16.4% increase in user reactivation in selected experiments.
• Integrated data processing, model training, and optimization workflows to enable repeatable model iteration across markets including Mexico, Egypt, and Brazil.
• Packaged and deployed the modeling pipelines via the internal data platform, using serialization and shell-based execution to support automated execution and reuse.

### Utility Data Analyst (Backend & Data Systems) @ GridX, Inc.
Jan 2020 – Jan 2022 | Milpitas, CA
• Designed and deployed end-to-end billing and ETL pipelines, processing 10k+ utility bills daily and converting raw meter data into reliable monthly usage aggregates, reducing data inconsistencies and improving downstream reporting reliability.
• Developed Java-based backend modules for New Energy Metering (NEM), improving billing accuracy and contributing to a 12% increase in revenue.
• Developed and deployed Python-based machine learning models and core business APIs to support billing validation, operational forecasting, and daily utility billing workflows, reducing manual reporting effort by ~10 hours per week.


## Education
### Master's degree in Computer and information technology
University of Pennsylvania

### Master of Science - MS in Statistic
University of Virginia

### Bachelor of Science - BS in Statistics
Zhongnan University of Economics and Law


## Contact & Social
- LinkedIn: https://linkedin.com/in/linli-wang-3a5350159

---
Source: https://flows.cv/linli
JSON Resume: https://flows.cv/linli/resume.json
Last updated: 2026-03-29