University of California, Riverside
M.S. in Computer Science
Sep. 2024 - Mar. 2026
Riverside, CA
Coursework: DBMS (A+), Machine Learning, Artificial Intelligence, High Performance Computing, GPU Architecture, Advanced Networks
Software Engineer - Backend & AI Platform / Enterprise RAG
Mingyang Li
I build retrieval-heavy backend systems that turn enterprise documents into traceable, low-latency AI workflows.
Recent M.S. Computer Science graduate focused on backend systems, enterprise RAG, AI platform engineering, and retrieval infrastructure. My work spans reactive Spring services, hybrid vector/full-text retrieval, transaction-oriented order flows, cache consistency, and production-readiness patterns for multi-tenant AI systems.
Fremont, CAActively seeking full-time Software Engineer roles in Backend, AI Platform, and Enterprise RAG.
Primary domain
Enterprise RAG
Backend proof
Orders + inventory
Retrieval layer
PgVector + RRF
Systems focus
Tenancy + audit
Technical Skills
Languages
Java 17PythonSQLC/C++JavaScriptGo
Backend
Spring Boot 3.xWebFluxProject ReactorREST/SSE APIsRedisPostgreSQL/PgVectorMySQLKafkaDockerMinIO
AI / Retrieval
Enterprise RAGParent-child chunkingHybrid vector/full-text retrievalRRF fusionHeuristic rerankingCitation-aware contextSpring AI concepts
Infrastructure
LinuxGitHub ActionsAWS fundamentalsCI/CDDistributed-system debuggingJVM fundamentals
Education
Shanxi University
B.E. in Software Engineering
Sep. 2020 - Jun. 2024
Taiyuan, China
Expertise
Backend infrastructure for retrieval-heavy AI products.
My strongest work sits at the boundary between AI retrieval quality and classical backend reliability, including transactional order systems.
Ingestion to answer pipeline
Enterprise RAG Backend
Designing document ingestion, metadata storage, chunk lifecycle, and query APIs for enterprise-aware knowledge systems.
Vector + full-text + evidence
Hybrid Retrieval & Citation Context
Combining PgVector search, PostgreSQL full-text search, RRF fusion, reranking, parent expansion, and citation-preserving context budgets.
REST/SSE + checkout flows
Reactive & Transactional Backend APIs
Building Spring services across AI query APIs and business-critical order flows, with idempotency, state transitions, timeouts, retries, and graceful fallbacks.
Tenancy, audit, cache, health
Distributed System Readiness
Adding the production slice around AI services: tenant filtering, Redis state, audit events, health checks, and operational logs.
Research Experience
Evaluation work for AI systems that need measurable robustness.
Graduate Research Assistant
RIPLE Research Group, UC Riverside
Advisor: Prof. Qian Zhang
Sep. 2025 - Present
Riverside, CA
- Built Python experiment runners and model adapters for GRAphRef, a constraint-guided fuzz-testing framework for 3D mesh AI models.
- Standardized evaluation across 8 mesh-processing systems including MeshCNN and HodgeNet, producing repeatable logs and metric reports.
- Ran structural mutation experiments for Valid Input Rate (VIR) and Semantic Preservation Score (SPS), then generated benchmark artifacts and LLM-output verification scripts using Benford/Zipf-style distributional checks.
Selected Projects
Systems projects shaped around retrieval, concurrency, and agent workflows.
PROJECT_01Backend
Jan. 2026 - Present
NexusAgent - Enterprise-Aware Knowledge Assistant Backend
A retrieval-first AI backend for enterprise documents, built around ingestion reliability, hybrid search quality, and citation-aware answer generation.
JavaSpring Boot 3.xWebFluxProject ReactorPostgreSQL/PgVectorRedisMinIODocker
- Built MinIO raw-file storage, PostgreSQL document/chunk metadata, parent-child chunking, child-only PgVector embeddings, and idempotent ingestion/re-chunking flows.
- Implemented vector and full-text retrieval, fused candidates with 1-based RRF, applied heuristic reranking, and expanded parent context for stronger evidence coverage.
- Exposed REST/SSE query APIs and a deterministic Plan-Execute-Critique workflow with Reactor timeouts, retries, fallback handling, trace IDs, Redis-backed session state, tenant-aware cache keys, audit events, and health/info endpoints.
PROJECT_02Backend
May 2025 - Aug. 2025
High-Concurrency Order & Inventory Backend
A transaction-oriented backend that demonstrates core systems fundamentals: retry-safe checkout, inventory access paths, cache consistency, and asynchronous order lifecycle handling under concurrent traffic.
JavaSpring BootMySQLRedisMessage QueueRPC FrameworkDistributed SchedulerDocker
- Designed MySQL schemas and composite indexes around the real access paths: item lookup, order-status queries, inventory checks, and user order history.
- Modeled pending, paid, cancelled, and expired order states with idempotency keys, duplicate-submission checks, and retry-safe checkout behavior.
- Implemented expiration and compensation flows with message-queue retries, scheduled workers, Redis/MySQL cache-aside patterns, delayed invalidation, and isolated thread pools for slow downstream operations.
PROJECT_03Backend
Oct. 2025 - Present
AI Agent Engineering Lab
A practical sandbox for testing model backends, prompt workflows, tool-use agents, and CI-backed engineering experiments.
DockerLinuxPythonLocal/Remote LLM BackendsAgent FrameworksGitHub Actions
- Built a Dockerized environment for local and remote LLM backends, comparing context-window behavior, memory usage, request latency, and deployment trade-offs.
- Wrote reusable Python scripts to replay prompts and tool-call workflows, collect structured logs, and document provider/backend configuration differences.
- Maintained lightweight CI checks for tests, formatting, environment validation, setup docs, and known failure modes across personal experiments.
Curriculum Vitae
Resume-ready details, embedded.
Current resume with education, research, backend projects, and AI platform work.
Contact
Backend and AI platform work is where I am aiming next.
Actively seeking full-time Software Engineer roles in Backend, AI Platform, and Enterprise RAG. I am especially interested in teams where retrieval infrastructure, backend reliability, high-concurrency business systems, and applied AI meet real product constraints.