Open to opportunities

Benjamin Dong

@benjamindong

Message

Senior AI/ML Engineer and Full-Stack Developer building production-grade generative AI and RAG systems.

United States

Message

What I'm looking for

I seek roles building production generative-AI and RAG systems where I can lead end-to-end ML/NLP engineering, scale reliable services, and deliver user-centric AI with strong privacy and performance practices.

I am a Senior AI/ML Engineer and Full-Stack Developer with a proven track record designing and deploying production-grade generative AI solutions, RAG systems, and multi-agent AI workflows. I build end-to-end platforms using LangChain, vector databases, LLM integrations, and scalable backend architectures to deliver reliable, privacy-aware AI for real users.

My career spans high-impact roles where I improved retrieval accuracy to 95%, reduced client workload by over 60% through automation, and increased discovery accuracy by 35% via AI-driven recommendation engines. I combine strong NLP and ML model work (fine-tuning BERT/GPT, PyTorch/TensorFlow) with full-stack development (Python, FastAPI, React/Next.js) and cloud deployment (AWS/GCP, Docker, CI/CD) to ship robust, user-centric products.

Experience

Work history, roles, and key accomplishments

Senior AI/ML Engineer

VengoAI

Sep 2023 - Sep 2025 (2 years)

Led development of a generative AI platform, implementing embeddings and vector search to achieve 95% answer retrieval accuracy and building multi-agent RAG pipelines that reduced client workload by over 60%.

Python Pinecone fastAPI Vector Databases React

AI Software Engineer

SphereInc

May 2022 - Jul 2023 (1 year 2 months)

Built NLP pipelines and a RAG recommendation engine using Pinecone and BERT, improving discovery accuracy by over 35% and delivering low-latency FastAPI microservices integrated with OpenAI and custom models.

Python Pinecone fastAPI OpenAI BERT PostgreSQL React Microservices

AI Engineer

SimuHealth

Jan 2021 - Apr 2022 (1 year 3 months)

Developed RAG pipelines and AI agent workflows for a virtual health assistant, implemented FastAPI microservices for symptom classification, and trained ML models to improve clinical extraction and intent detection while reducing hallucinations.

Python ChromaDB fastAPI PyTorch BERT AI Training AWS React

Full Stack Developer

Disqus

Jun 2018 - Dec 2020 (2 years 6 months)

Developed and maintained Django backend services and React/Next.js interfaces for a high-traffic discussion platform, improving performance through PostgreSQL tuning, Redis caching, and CI/CD deployments on AWS.