Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I'm Mike Hoang Tran, a Senior LLM & AI Platform Engineer based in Houston. I design and operate production-grade LLM and RAG systems, with a focus on secure, compliant architectures for regulated enterprises. Over the past 7+ years, I've led cross-functional teams and built retrieval pipelines and tool orchestration with LangChain/LangGraph to deliver impactful AI solutions. My work spans CareFirst, MobiDev, and ADP, where I helped improve efficiency, reduce latency, and enable thousands of internal users to work effectively with AI.…I'm Mike Hoang Tran, a Senior LLM & AI Platform Engineer based in Houston. I design and operate production-grade LLM and RAG systems, with a focus on secure, compliant architectures for regulated enterprises. Over the past 7+ years, I've led cross-functional teams and built retrieval pipelines and tool orchestration with LangChain/LangGraph to deliver impactful AI solutions. My work spans CareFirst, MobiDev, and ADP, where I helped improve efficiency, reduce latency, and enable thousands of internal users to work effectively with AI.

Mike Hoang Tran

AI Engineer, Data Scientist, Full Stack Developer, +2





I'm Mike Hoang Tran, a Senior LLM & AI Platform Engineer based in Houston. I design and operate production-grade LLM and RAG systems, with a focus on secure, compliant architectures for regulated enterprises. Over the past 7+ years, I've led cross-functional teams and built retrieval pipelines and tool orchestration with LangChain/LangGraph to deliver impactful AI solutions. My work spans CareFirst, MobiDev, and ADP, where I helped improve efficiency, reduce latency, and enable thousands of internal users to work effectively with AI.…I'm Mike Hoang Tran, a Senior LLM & AI Platform Engineer based in Houston. I design and operate production-grade LLM and RAG systems, with a focus on secure, compliant architectures for regulated enterprises. Over the past 7+ years, I've led cross-functional teams and built retrieval pipelines and tool orchestration with LangChain/LangGraph to deliver impactful AI solutions. My work spans CareFirst, MobiDev, and ADP, where I helped improve efficiency, reduce latency, and enable thousands of internal users to work effectively with AI.

Available to hire

I’m Mike Hoang Tran, a Senior LLM & AI Platform Engineer based in Houston. I design and operate production-grade LLM and RAG systems, with a focus on secure, compliant architectures for regulated enterprises. Over the past 7+ years, I’ve led cross-functional teams and built retrieval pipelines and tool orchestration with LangChain/LangGraph to deliver impactful AI solutions. My work spans CareFirst, MobiDev, and ADP, where I helped improve efficiency, reduce latency, and enable thousands of internal users to work effectively with AI.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

English

Fluent

Work Experience

Senior AI Engineer at CareFirst BlueCross BlueShield

November 1, 2024 - October 1, 2025

Architected 'ClaimGuard,' a HIPAA-compliant RAG assistant serving 8k internal users; reduced policy lookup time by 42% by orchestrating LangChain pipelines over pgvector + Pinecone. Led a 5-engineer tiger team implementing LangGraph-powered agent workflows that triaged claims documents and routed outputs to Python toolkits and human reviewers. Built automated evaluation harnesses with LangSmith and custom guardrails, driving 18% QoQ quality uplift. Owned FastAPI services and Kafka ingestion stack that unified 1.2TB of regulated documents, added semantic metadata, Azure Cognitive Search fallbacks, and encrypted caches. Instituted DDD-aligned microservice boundaries, IaC via Terraform, and GitHub Actions CI/CD with policy-as-code checks to keep deployments safe and auditable. Led enablement workshops for 50+ analysts on AI-assisted workflows.

Applied AI Engineer at MobiDev

July 1, 2022 - June 1, 2024

Delivered forecasting and simulation pipelines for retail/CPG clients, combining classic ML with LLM-based insight generation; cut forecasting errors to ~2%. Introduced Retrieval-Augmented experimentation lab using Weaviate + LangChain to let analysts query model diagnostics conversationally. Implemented automated training/eval workflows in Airflow + MLflow, including feature stores, lineage tracking, and drift alerts. Containerized ML services with Docker/Kubernetes and automated retraining + deployment pipelines on AWS for faster iteration.

Software Engineer at ADP

November 1, 2019 - March 1, 2022

Built anomaly-detection services for workforce dashboards, leveraging embeddings + heuristics to flag payroll irregularities; kept false positives under 3%. Designed full-stack dashboards (React + GraphQL + Python microservices) with real-time WebSocket updates, serving 25k enterprise users. Established shared API contracts, schema validation, and CI testing that accelerated release cadence from monthly to weekly.