Open to opportunities

Benjamin Dong

@benjamindong1

Message

Senior Backend & AI Engineer specializing in production RAG systems, Python backends, and cloud deployments.

United States

Message

What I'm looking for

I seek roles where I can build and operate production AI platforms—focused on scalable, secure RAG systems, strong engineering ownership, cloud deployments, and measurable reliability and compliance.

I am a Senior Backend & AI Engineer with 8+ years building production-grade AI systems, focused on hardcore Python backend development, LangChain, and LangGraph. I design and operate enterprise Retrieval-Augmented Generation (RAG) systems that deliver high-throughput, low-latency performance across regulated domains.

I have led end-to-end projects from data ingestion to inference and monitoring, building FastAPI services, vector search pipelines (Pinecone, ChromaDB, Qdrant), and LLM orchestration that achieved strong retrieval precision and reduced unsafe outputs through evaluation frameworks. I own cloud deployments on AWS and Azure, integrating CI/CD, observability, and compliance controls for GDPR- and HIPAA-aligned systems.

I translate complex business processes into scalable, secure, and observable backend AI platforms, with hands-on experience in agentic workflows, multi-step execution, embedding and re-ranking strategies, and production telemetry to ensure reliability and traceability.

Experience

Work history, roles, and key accomplishments

Senior Backend & AI Engineer

VengoAI

Sep 2023 - Sep 2025 (2 years)

Built and operated production RAG systems and LangGraph-based agent architectures supporting thousands of daily workflows, achieving 95% top-5 retrieval precision and sustaining 10K+ RPM with sub-200ms p95 latency. Implemented PII detection, audit logging, and retention policies to enable GDPR-aligned enterprise deployments while maintaining 99.99% uptime.

Python LangGraph fastAPI Pinecone Vector Search AWS Azure CI CD Observability

AI Backend Engineer

MoovAI

May 2022 - Jul 2023 (1 year 2 months)

Developed production recommendation RAG pipelines over 300K+ records, achieving 90%+ top-5 relevance precision and reducing irrelevant results by 50% through multi-stage retrieval and LLM re-ranking. Deployed scalable FastAPI services on AWS EKS with sub-300ms average latency under concurrent traffic.

Python fastAPI Vector Search Embeddings OpenAI Claude Prompt Versioning Monitoring

AI Engineer

SimuHealth

Jan 2021 - Apr 2022 (1 year 3 months)

Designed and deployed a clinical RAG system over 200K+ medical records for real-time triage, reducing unsafe recommendations by 45% via multi-stage validation and risk scoring. Built secure FastAPI services on AWS ECS Fargate with sub-300ms latency and HIPAA-aligned data governance controls.

Python fastAPI ChromaDB Vector Search AWS Fargate HIPAA Évaluation Monitoring

Full Stack Developer

Disqus

Jan 2019 - Dec 2020 (1 year 11 months)

Developed high-traffic Python/Django backend services for authentication, commenting, and moderation used by millions daily, improving API response times via PostgreSQL optimizations and Redis caching. Implemented asynchronous background pipelines and operated services on AWS EC2 to maintain high availability.

Python Django PostgreSQL Redis AWS EC2 REST APIs Monitoring Authentication Role Based Access Control

Education

Degrees, certifications, and relevant coursework

National Taiwan University

Bachelor of Science, Computer Science

2014 - 2018

Completed a Bachelor of Science in Computer Science at National Taiwan University with coursework and projects focused on software engineering and algorithms.