Available for new opportunities

Tran Quoc Truong

Product Engineer · Applied AI · Backend Systems

Building production-grade AI systems & backend platforms.

I build agentic applications, RAG platforms, and backend systems, with a focus on production reliability, observability, and evaluation.

View Featured Work Download CV (PDF)

Ho Chi Minh City, Vietnam · GitHub ↗ · LinkedIn ↗ · [email protected]

Tran Quoc Truong

Product Engineer · Applied AI & Backend Systems

Engineering Evidence

Featured Work

Production-grade systems demonstrating agentic architectures, automated verification, and enterprise code intelligence.

View all 9 case studies

Flagship AI Platform 2026–Present

Omni-Agent — AI Platform

Platform for building knowledge bases, running AI agents, and evaluating agent behavior

A modular Applied AI platform featuring document intelligence with Docling and Qdrant, a Streamable HTTP MCP server, a LangGraph-based multi-agent runtime, and an integrated Agent Assurance evaluation engine.

Platform Architecture: Engineered a modular monorepo featuring a Django/DRF control plane for project tenancy, identity, and permissions, backed by decoupled, stateless Celery workers for asynchronous processing workloads.

Knowledge Builder: Built document processing pipeline with Docling layout parsing/OCR, snapshot chunking, Qdrant vector indexing, a Streamable HTTP MCP tool server, and a LangGraph-based multi-agent runtime with citation-grounded RAG.

Agent Assurance (IVS Hackathon 2nd Place): Implemented execution evidence capture through LiteLLM and OpenTelemetry, trace reconstruction pipelines to normalize multi-turn trajectories, and deterministic quality gates.

LangGraphFastAPIModel Context Protocol (MCP)OpenTelemetry (OTel)LLM-as-a-JudgeQdrant

View Case Study

Evaluation Infrastructure · 2nd Place IVS Hackathon 2026

Agent Assurance (ATA) — AI Agent Evaluation Platform

Quality & evaluation infrastructure for autonomous AI agents

An independent validation and audit layer for agentic systems that captures runtime interactions via LiteLLM and OpenTelemetry, reconstructs execution traces, and enforces deterministic quality gates.

Built an end-to-end evaluation engine with a FastAPI control plane, LiteLLM gateway, Celery workers, PostgreSQL, Redis, and an operational dashboard.

Designed a multi-stage evaluation workflow using Planner, Judge, Critic, and Meta-Judge roles across configurable quality dimensions.

Implemented percentile-based quality gates and deterministic critical blockers to produce reproducible PASS/FAIL verdicts.

Agent EvaluationOpenTelemetryLLM-as-a-JudgeFastAPICeleryLiteLLM Gateway

View Case Study

Enterprise Applied AI 2026

IQP — Intelligent Quality Platform

AI-assisted traceability and code intelligence for enterprise systems

An enterprise platform combining graph-based product knowledge, source-code intelligence, and hybrid retrieval to automate engineering traceability and test analysis.

Designed backend service boundaries for workspace management, graph ingestion and retrieval, code indexing, AI context access, and quality-analysis workflows.

Implemented hybrid retrieval combining semantic, lexical, and graph-based signals to provide scoped context for engineering and AI-assisted tools.

Developed code-intelligence capabilities for indexing source repositories and linking product concepts with related implementation and test assets.

FastAPIQdrantPostgreSQLRedisCeleryMCP

View Case Study

Core Focus

What I Build

Engineering solutions spanning autonomous agent workflows, distributed backend systems, and software reliability engineering applied to generative AI.

End-to-End System Architecture Pipeline Production Workflow

Stage 1

Agents & Orchestration

Stage 2

Knowledge & Hybrid RAG

Stage 3

Backend Control Plane

Stage 4

OTel Trace & Evaluation

AI Systems

Autonomous multi-agent orchestration, contextual retrieval, and grounded reasoning built on real operational data.

LangGraph Runtimes: Stateful subgraphs, routing, and verifiers
Model Context Protocol (MCP): Streamable HTTP tool servers
Knowledge Processing: Docling layout OCR & multi-vector Qdrant RAG
Model Customization: LoRA fine-tuning & prompt optimization

Backend Platforms

Scalable control planes, distributed asynchronous workflows, and clean domain boundaries.

High-Performance APIs: FastAPI, Django/DRF, and SSE streaming
Async Orchestration: Decoupled Celery workers and Redis queues
Data Layer: PostgreSQL schemas, SQLAlchemy ORM, and MinIO S3 storage
Platform Orchestration: Docker Compose, Nginx reverse proxy, and Linux

Reliability & Evaluation

Software testing discipline applied to probabilistic AI systems, observability, and deterministic quality gates.

Trace Reconstruction: OpenTelemetry & LiteLLM trajectory normalization
Adversarial Evaluation: Planner → Judge → Critic → Meta-Judge roles
Deterministic Gates: P10/P50 percentile metrics & blocker checks
Security Testing: Prompt injection defense, data leakage audits

Career Trajectory

Work Experience

Engineering delivery across applied AI, agent evaluation, backend architecture, and enterprise systems.

Applied AI Engineer & Automation Tester

FPT Software · Ho Chi Minh City, Vietnam

Dec 2024 — Present

IQP (Code Intelligence & Quality Retrieval): Architected backend retrieval for IQP combining semantic vector search, BM25 lexical signals, and Code Graphs, exposing contextual tools to AI clients via Model Context Protocol (MCP) to automate quality analysis across multi-repository codebases.
Agent Assurance (Evaluation & Observability Engine): Architected and implemented an end-to-end AI Agent Verification engine (awarded 2nd Place at IVS Hackathon 2026) featuring runtime evidence capture via LiteLLM and OpenTelemetry, trace reconstruction pipelines, and deterministic quality gates.
AI Systems Reliability & Assurance Lifecycle: Established an end-to-end assurance lifecycle spanning Intake, Requirements, Test Design & Oracle Definition, Measurement Qualification, Behavioral Validation, Reporting, and Re-assurance for agentic applications.
Banking Automation & Systems Verification: Engineered reusable cross-platform test automation and 1,500+ lines of SQL validation across banking and payment systems, cutting manual regression effort by ~70%.

Full-Stack Developer Intern

FPT Software Academy · Ho Chi Minh City, Vietnam

Sep 2024 — Dec 2024

Built the core backend for an online learning and assessment platform using Django with role-based access control and automated exam workflows.
Integrated a separate FastAPI computer-vision service for AI-assisted real-time exam proctoring and face detection.
Containerized and deployed the multi-service architecture using Docker Compose, Nginx reverse proxy, and Cloudflare Tunnel.

Engineering Capabilities

Technical Skills

Practical stack coverage across model workflows, service boundaries, and quality gates.

AI & Agent Systems

LangGraphMulti-Agent SystemsModel Context Protocol (MCP)Tool CallingCitation-Grounded RAGHybrid RetrievalVector Search (Qdrant, Milvus)Docling Layout & OCREmbeddingsLoRA Fine-Tuning

Backend Engineering

PythonFastAPIDjango / DRFPostgreSQLRedisCelerySQLAlchemyPydanticREST APIs & SSEAsync WorkflowsIdempotency Contracts

AI Infrastructure & Observability

OpenTelemetry (OTel)LiteLLM GatewayDockerDocker ComposeMinIO (S3-Compatible)NginxLangfuseLinuxCI/CD

Reliability & System Design

System ArchitectureLLM-as-a-JudgeDeterministic Quality GatesRuntime Trace ReconstructionPrompt Injection TestingAPI VerificationEvaluation BenchmarksData Integrity & Auditability

Honors & Awards

Recognition in competitive hackathons and academic research.

2nd Runner-up Aug 2026

2nd Place — IVS Hackathon 2026

IVS Hackathon 2026 (FPT Software) · Nova4Test · IVS HCM

Awarded 2nd place for independently architecting an end-to-end AI Agent Verification engine (Agent Assurance) featuring runtime evidence capture, trace-based behavioral evaluation, and governed quality gates; subsequently integrated into Omni-Agent.

Team Nova4Test receiving 2nd Runner-up award at IVS Hackathon 2026 — Award Ceremony: Team Nova4Test awarded 2nd Runner-up at IVS Hackathon 2026

Tran Quoc Truong pitching the Agent Assurance engine on stage — Technical Defense: Truong presenting the agent evaluation architecture before judges

Explore Agent Assurance Case Study

Second Prize (Giải Nhì) Apr 2024

Second Prize — Autonomous Driving Research Paper Competition

Student Research Paper Competition · FPT University

Co-authored research combining YOLOv8 perception, lane segmentation, and PID steering control in Unity simulation, completing the autonomous benchmark in 125.8 seconds with a perfect 100% score.

Second Prize award certificate at Research Paper Competition Spring 2024 — Award Ceremony: Second Prize in Student Scientific Research Competition (IT Division)

Explore Self-Driving Car Case Study

Academic Foundations

Education

Formal software engineering and artificial intelligence training.

Master of Software Engineering in AI

FPT School of Business & Technology

May 2026 — Present

Software engineering focus for applied AI systems.

Bachelor of Artificial Intelligence

FPT University

2021 — 2025

Computer vision, machine learning, AI evaluation, and LLM systems.

Project Archive

More Engineering Projects

Earlier systems, capstones, and industry deliveries.

Browse complete catalog (9 case studies) →

2025

APIT — Agent Programmatic Integration Testing

An AI-assisted API testing application that generates structured test scenarios from API documentation.

Read case study →

2024-2026

Core Banking & Payment Hub QA Automation

Client delivery work covering Core Banking and Payment Hub integrations across API, database, web, mobile, regression, and automation testing.

Read case study →

2025

E-Commerce AI Assistant

An end-to-end AI shopping assistant that combines filtered vector search and agent-driven conversational retrieval for natural-language product discovery.

Read case study →

2024

LMS — Learning & Assessment Platform

A full-stack learning and assessment platform covering structured course content, enrollment, quizzes, reporting, role-based workflows, and a separately deployed face-detection service.

Read case study →

2024

Self-driving Car Problem

A simulated autonomous-driving pipeline combining YOLOv8-based perception, lane segmentation, OpenCV processing, and PID steering control inside a Unity environment.

Read case study →

2024

Leaf-Based Plant Disease Detection

A PyTorch computer-vision pipeline for plant disease classification that combines image preprocessing, CNN inference, class-specific thresholds, and Grad-CAM++ explanations behind a FastAPI service.

Read case study →

Open to Opportunities

Let's build reliable AI and backend systems together.

Seeking Product Engineer, Applied AI Engineer, and Backend Platform roles. Open to discussing agent architectures, evaluation pipelines, and production delivery.

Send Email Connect on LinkedIn ↗ Download Full CV (PDF)