Enterprise Multi-Agent Platform
Agentic AI · LangGraph · MCP
Production-grade multi-agent platform with tool calling, inter-agent communication, and multi-tenant orchestration for enterprise workflows.
LangGraphLangChainFastMCPFastAPI
Read more AI Engineer•Agentic AI•RAG · Data Platforms
Building EnterpriseAI Agents ThatShip to Production
I'm Nguyễn Hải Lâm — AI Engineer at Viettel Cyber Security. I design and build production-grade agentic systems, multi-tenant RAG platforms, and the data infrastructure that powers them.
3+
Years in AI Engineering
5+
Organizations
1M+
Records Processed
National AI
Olympiad 2025
Trusted by teams at
Viettel Cyber SecurityAIZHBLabĐấu ThầuPTIT IECHuaweiVTV3 OlympiaIEEEViettel Cyber SecurityAIZHBLabĐấu ThầuPTIT IECHuaweiVTV3 OlympiaIEEE
What I Do
Crafting AI as software,
not as a parlor trick.
Four overlapping practices I bring to every engagement — from the first whiteboard sketch to the dashboard you check at 2am. Each one ships with evals, observability, and a runbook.
Evals includedCost-awareProduction-grade
01
Agentic AI Systems
Multi-agent platforms with LangGraph, MCP and tool use — engineered for real business workflows, not just demos.
Available
02
LLM Applications
Production LLM products on OpenAI, Llama, Claude — with evals, guardrails, cost control and proper observability.
Available
03
RAG Infrastructure
Multi-tenant RAG platforms — parsing, chunking, embeddings, hybrid search, reranking and retrieval QA.
Available
04
Data & Backend
FastAPI services and Spark / Kafka pipelines — clean architecture, async by default, scales calmly.
Available
About Me
Nguyễn Hải Lâm — AI Engineer at Viettel Cyber Security, based in Hanoi. Bachelor of Artificial Intelligence (PTIT, GPA 3.45/4.0), IEEE author, and a National AI Olympiad 2025 winner.
3+ years across 5 organizations shipping agentic platforms, multi-tenant RAG, and data infrastructure — from research to product to production. Past lives include AI Engineer / PM at AIZ, LLM engineer at HBLab, legal AI at Đấu Thầu, and teaching assistant at PTIT IEC mentoring 200+ students.
Agentic AILLM EngineeringRAG SystemsData EngineeringBackend EngineeringAI PlatformMulti-AgentProduction AIResearch → Product
Experience
- Viettel Cyber SecurityArtificial Intelligence Engineer — Enterprise AI, LLM apps, security2026 – Present
- AIZAI Engineer / Project Manager — Multi-Agent, LangGraph, multi-tenant RAG2025 – 2026
- HBLabJunior LLM Engineer — Google ADK, AI testing agent, test generation2025
- Đấu Thầu EcosystemJunior AI Engineer — Legal AI, hybrid search, multi-agent RAG, MCP2024 – 2025
- PTIT IECLLM Engineer — Research, AI teaching assistant, AI education2023 – 2025
How I Work
A calm, repeatable process.
Same loop, every project. It bends with the problem but never breaks the discipline.
01
Discover
Understand the user, the data, and the unfair business edge AI should create.
02
Design
Sketch the system — prompts, retrieval, evals, latency budget and failure modes.
03
Build
Ship a thin vertical slice fast, then harden with tests, logs and dashboards.
04
Iterate
Measure with real users, kill what doesn't work, double down on what does.
Proficiency
Where I'm sharpest.
Agentic AI · LangGraph · MCP95%
LLM Engineering & Evals93%
RAG & Vector Search (Qdrant / Pinecone)92%
Python / FastAPI Backend90%
Data Engineering (Spark / Kafka)85%
DevOps & Observability80%
12+
RAG systems
8
Production agents
99.9%
Service uptime
Featured Projects
TestGen — AI QA Agent
Agentic AI · QA Automation
Agent that reads PRD/SRS and auto-generates test cases, slashing QA time, lifting coverage, and standardizing the test process.
Google ADKSeleniumAppiumPython
Read more 
AMI Chatbot — RAG Assistant
RAG · LLM · Production
Production RAG assistant for PTIT — real-time knowledge retrieval over institutional data, deployed for thousands of students.
LangChainQdrantFastAPIMongoDB
Read more 
GitHub Analyzer — Data Platform
Data Engineering · 1M+ records
Large-scale pipeline analyzing 1M+ GitHub records — streaming ingestion, lakehouse storage, and analytical queries.
SparkKafkaDuckDBMinIO
Read more 
Enterprise RAG Platform
RAG Infrastructure · Multi-Tenant
End-to-end RAG infrastructure — parsing, chunking, embeddings, hybrid retrieval and reranking with strict tenant isolation.
QdrantPineconeFastAPIPostgreSQL
Read more HimLamTech — AI Career Platform
Software · AI Product
AI-assisted career platform: resume parsing, job matching, and career recommendations powered by vector search.
NextJSFastAPIQdrantPostgreSQL
Read more Tech Stack
AI / LLM
OpenAILangGraphLangChainLlamaIndexAutoGenGoogle ADKFastMCP
Data
SparkKafkaPostgreSQLQdrantPineconeMongoDBRedisMinIO
Backend
FastAPIPythonDockerNginxRabbitMQ
Observability
LangFuseLangSmithPrometheusGrafana
Research
IEEE AuthorAgentic AIRAGRLSynthetic DataUML Generation
Awards & Achievements
National AI Olympiad 2025
Hội Tin học Việt Nam
Posts and Telecommunications Institute of Technology
Northern Regional AI Olympiad 2025 — 3rd
Northern Region, Vietnam
Top finisher in Northern regional bracket
First Prize — VietFuture 2024
VietFuture
National innovation competition
Third Prize — VNU AI Hackathon 2024
Vietnam National University
AI hackathon, third place finalist
Top 10 — Huawei Seeds For The Future 2023
Huawei
Selected from a national applicant pool
Road To Olympia 21
VTV3 — Vietnam Television
Đường Lên Đỉnh Olympia, season 21 contestant
Engineering Philosophy
- Treat AI as software engineering, not magic.
- Build for real users in production, not for demos.
- Prefer simple systems that scale over complex hype.
- Optimize for reliability, observability, and impact.
- Move from research to product — and keep shipping.
Kind Words
What collaborators say.
"Hải Lâm thinks about AI the way good engineers think about distributed systems — evals, latency, observability, cost. Calm execution, every time."
SE
Senior Engineering Lead
Viettel Cyber Security
"He owned our multi-agent platform end-to-end. LangGraph, MCP, multi-tenant — production-grade from day one."
PD
Product Director
AIZ
"Rare combination: research depth, product taste, and the discipline to ship. Our QA agent shipped in weeks, not quarters."
TL
Tech Lead
HBLab
Writing
Notes from the workshop.
Field notes on building AI systems that survive contact with real users — from retrieval edge cases to agent failure modes.
Read all essays01
Agents May 2026· 11 min read
Designing multi-agent systems that don't lose their mind in production
02
RAG Mar 2026· 9 min read
Why naive RAG is not enough — and the multi-tenant playbook that works
03
Evals Jan 2026· 7 min read
A practical eval harness for LLM features at enterprise scale
Frequently asked
What kind of engagements do you take on?
Agentic AI platforms, multi-tenant RAG infrastructure, LLM products, and AI-heavy backends. Greenfield builds or rescuing AI prototypes that need to ship to production.
Do you work remote or on-site?
Based in Hanoi. I work full-time at Viettel Cyber Security and collaborate remotely with selected teams across Vietnam, SEA, and EU/US time zones.
What's your default stack?
LangGraph + FastMCP for agents, Qdrant / Pinecone for retrieval, FastAPI + Python on the backend, Spark / Kafka on data, LangFuse + Grafana for observability.
Can clients trust you with production AI?
Yes — production systems at Viettel Cyber Security and AIZ, 1M+ records processed in data pipelines, IEEE-published research, and a national AI award. Engineering discipline backs every shipped feature.