Résumé
Sang Truong
Senior AI Engineer · Applied AI Lead
Ho Chi Minh City, Vietnam · GitHub @sangtrx
Professional summary
Senior AI engineer and technical lead with 6+ years across LLM/RAG/agent systems, computer vision and video intelligence, multimodal learning, quantitative ML, time-series forecasting, speech AI, edge inference, and production AI engineering. I own systems end to end from research and data acquisition through model/tool design, APIs, distributed workloads, GPU/edge optimization, product surfaces, deployment, observability, reliability, and stakeholder delivery. Master of Engineering (MEng) in Computer Engineering with a 4.0/4.0 GPA and peer-reviewed work across IJCV, AAAI, IEEE JBHI, Poultry Science, IEEE Access, ICIP, BMVC, and IEEE BHI.
Domain depth
Applied AI · Agents · Voice · RAG
Production AI systems where retrieval, tools, memory, voice/real-time interaction, authority, safety, evaluation, and distributed application state matter as much as the model call.
- Ho Chi Minh City Traditional Medicine Hospital clinical AI: one semantic owner for request/reference/source/tool/scope, bounded approved-corpus research, durable Evidence Workspace, deterministic clinical authority and exact citations
- FPT AI4U: Azure OpenAI, LangGraph/LangChain, Qdrant RAG, tool/model routing, code execution, web search, memory controls and guardrails
- Voice and tool workflows: multilingual Azure Speech transcription/evaluation, Vietnamese ASR/TTS, WebSockets/SSE, Playwright-based browser verification and failure handling
FastAPI · LangGraph · LangChain · Azure OpenAI · Azure Speech · Qdrant · Milvus · pgvector · Playwright · Celery · RabbitMQ · Redis · PostgreSQL · Docker
Computer Vision · Video · Edge AI
Physical-world AI spanning camera/media ingest, perception, tracking, temporal events, evidence capture, edge inference, and recovery under unreliable real-world conditions.
- Production multi-camera video intelligence: YOLO11, Vietnamese ALPR, ByteTrack, line crossing, event video, identity/freshness checks, watchdog recovery
- University of Arkansas: temporal action understanding, vision-language modeling, industrial CV, CarcassFormer, YOLOv8 Jetson deployment
- 5D Agriculture: autonomous braking, face recognition, Intel RealSense D435 RGB-D livestock measurement, embedded AI
PyTorch · TensorFlow · OpenCV · YOLO11/YOLOv8 · Fast-ALPR · ByteTrack · TensorRT · CUDA · ONNX Runtime · Jetson · FFmpeg · MediaMTX
Quantitative Research · Trading Systems
A research-to-production stack built around point-in-time evidence, reusable causal computation, leakage/multiplicity control, durable signal/risk state, execution/reconciliation, and public verification boundaries.
- Curren research: Rust/Python causal core, Arrow/Parquet PIT evidence, shared timeframes/primitives/events, versioned event store, hypothesis views, global OOF and append-only Alpha History
- Curren production path: normalized external alpha-source data, fail-closed ML quality gate, restart-safe lifecycle/risk, guarded execution, reconciliation and research↔streaming parity
- Confidential Fund + Bluebelt: equity/crypto/FX quantitative research, ML ensembles, sentiment-derived signals, AWS execution and MLflow experimentation
Rust · Python · Arrow · PyArrow/Parquet · Polars · DuckDB · LightGBM · CatBoost · XGBoost · SciPy · Statsmodels · Optuna · NautilusTrader
Research · Multimodal & Temporal ML
Peer-reviewed research across temporal video understanding, vision-language learning, medical time-series representation learning, and industrial computer vision.
- ABN → AEI → AOE-Net: action boundaries and actor/object/environment interaction modeling for long untrimmed video
- VLCAP → VLTinT: contrastive vision-language learning and coherent video paragraph captioning; VLTinT was an AAAI 2023 Oral
- sCL-ST + CarcassFormer: medical time-series contrastive learning and industrial localization/segmentation/classification
Transformers · Contrastive Learning · PyTorch · TensorFlow · Detectron2 · MATLAB · NumPy · SciPy · Scikit-learn · Weights & Biases
Professional & research experience
Head of Artificial Intelligence · EPIC TECHNOLOGY
Leading architecture and delivery across clinical AI, education AI, production computer vision/video intelligence, and AI platform engineering; owning requirements decomposition, data/model contracts, APIs, authority boundaries, deployment, testing, observability, and stakeholder acceptance.
- Built the Ho Chi Minh City Traditional Medicine Hospital AI Chatbot & Clinical Decision-Support Platform, including a single semantic-owner clinical-agent path, bounded approved-corpus research, deterministic clinical authority, durable evidence state, exact citations, role-scoped access and auditability.
- Built an AI-powered Open edX platform with teacher-reviewable course generation, Milvus-backed AI tutoring, secure question context and answer-key handling, Vietnamese ASR/TTS, WebSockets, Live2D interaction, OLX automation, Tutor/Docker/Nginx operations, and Playwright verification.
- Built and operate a production multi-camera AI program with video acquisition, stream normalization, YOLO11 detection, Vietnamese ALPR, ByteTrack tracking, temporal event logic, evidence capture, monitoring, and automated recovery.
- Technologies include Python, FastAPI, AsyncIO, WebSockets/SSE, Next.js, React, PostgreSQL, pgvector/Qdrant, RabbitMQ, Celery, Open edX, Tutor/Django, Milvus, LangChain/LLMs, ASR/TTS, PyTorch, ONNX Runtime, OpenCV, YOLO11, Fast-ALPR, ByteTrack, MediaMTX, Docker, Nginx, Linux, and Playwright.
AI Tech Lead · Part-time / Consulting · A9 IOT
Leading real-time environmental IoT forecasting with continuous preprocessing, evaluation, inference, visualization, and stakeholder-facing reporting across LSTM, XGBoost, ARIMA, and Prophet workflows.
- Built continuous sensor preprocessing, model training/evaluation, inference, visualization, and reporting workflows.
- Technologies include Python, TensorFlow, XGBoost, ARIMA, Prophet, Pandas, NumPy, Matplotlib, and Jupyter.
AI Engineer · FPT Software
Built enterprise conversational agents and multilingual voice/real-time AI systems with Azure OpenAI, LangGraph/LangChain, Qdrant RAG, tool/model routing, distributed workers, guardrails, evaluation workflows, and production APIs.
- Developed AI4U with Azure OpenAI, LangGraph/LangChain orchestration, Qdrant-backed RAG, multi-stage dialogue state, model/tool routing, controlled code/tool execution, web search, diagram generation, memory controls, and content safety.
- Built multilingual recording/transcription and speech-evaluation services for English, Japanese, Korean, and Vietnamese with Azure Speech/OpenAI, FastAPI, Celery, RabbitMQ, Redis, distributed crawling, retries, and production controls.
- Technologies included Python, FastAPI, Azure OpenAI, Azure Speech, LangChain, LangGraph, Qdrant, NeMo Guardrails, RabbitMQ, Redis, Celery, MongoDB, Docker, Kubernetes, Playwright, and Azure Blob Storage.
Graduate Researcher / PhD Student Researcher & Teaching Assistant · University of Arkansas
Graduate research in multimodal video understanding, temporal representation learning, vision-language modeling, medical time-series learning, industrial computer vision, and real-time edge inference; completed an MEng in Computer Engineering during this period.
- Co-developed ABN, AEI, and AOE-Net for temporal action proposal generation and actor/object/environment interaction modeling in long untrimmed videos.
- Co-developed VLCAP and VLTinT for coherent video paragraph captioning; VLTinT was selected as an AAAI 2023 Oral.
- Worked on sCL-ST for multi-lead ECG arrhythmia classification and CarcassFormer/poultry-defect inspection for industrial computer vision.
- Built data/annotation workflows and optimized YOLOv8 on NVIDIA Jetson with TensorRT, FP16, CUDA streams, CUDA preprocessing, and memory-oriented tuning.
Selected independent side project
Curren · Independent AI/Quant Side Project · Solo Builder
A solo-built multi-system platform spanning point-in-time research evidence, shared Rust/Python causal event infrastructure, OOF/multiplicity governance, real-time signal intelligence, fail-closed ML quality filtering, lifecycle/risk/execution, access/distribution, and an isolated public verification layer.
Research evidence path active · live public feed/profitable alpha not claimed
Selected flagship systems under EPIC TECHNOLOGY
Ho Chi Minh City Traditional Medicine Hospital AI Chatbot & Clinical Decision-Support Platform
EPIC TECHNOLOGY · AI Architect / Lead Builder
Clinical assistant for drug/herb lookup, interaction analysis, prescription review and governed knowledge Q&A using a single semantic-owner agent path, bounded local evidence research, deterministic clinical authority, durable observation/evidence state, exact citations and auditability.
Production Multi-Camera Video Intelligence Platform
EPIC TECHNOLOGY · AI / Computer Vision Systems Lead
Real-time multi-camera system covering media acquisition, stream normalization, YOLO11 perception, Vietnamese ALPR, ByteTrack tracking, temporal event logic, evidence capture, alerts, access control, monitoring, and automated recovery.
AI-Powered Open edX Platform
EPIC TECHNOLOGY · AI Architect / Lead Builder
Teacher-reviewable course generation from textbooks/syllabi into lessons and OLX packages, plus Milvus-backed tutoring, secure question context and answer-key handling, Vietnamese ASR/TTS, WebSockets, Live2D browser interaction, Playwright verification, and Tutor/Docker/Nginx operations.
Additional industry experience
Quantitative Researcher / Data Scientist · Confidential Fund · NDA Project
- Developed alpha-focused equity prediction research using feature engineering, LightGBM/XGBoost ensembles, sentiment-analysis agents, iterative market-data evaluation/backtesting, constrained AWS execution, parallel processing, and MLflow experiment tracking.
AI Engineer / Data Scientist · Contract · Crypto Communities Chatbot Development
- Designed LLM/RAG community chatbots with LangChain and Pinecone for knowledge-grounded support automation across social platforms.
Quantitative Researcher / Data Scientist · Bluebelt Group
- Built Python/FastAPI infrastructure for cryptocurrency and FX trading signals and quantitative/ML experimentation, providing an early production foundation for later fund and Curren research work.
AI Engineer · Computer Vision / Embedded AI · 5D Agriculture Solutions JSC
- Built computer-vision systems for autonomous braking, face-recognition attendance, and contactless livestock-weight estimation with Intel RealSense D435 RGB-D sensing.
- Worked across camera acquisition, image/depth preprocessing, model inference, application/control logic, NVIDIA Jetson/Raspberry Pi integration, and real-time system behavior.
Research trajectory
Temporal action understanding
ABN → AEI → AOE-Net: action-boundary and actor/object/environment interaction modeling for long untrimmed video, culminating in IJCV.
Vision-language video understanding
VLCAP → VLTinT: contrastive and Transformer-based modeling for coherent video paragraph captioning; VLTinT was selected as an AAAI 2023 Oral.
Medical & industrial ML
sCL-ST for multi-lead ECG representation learning and CarcassFormer for poultry defect localization, segmentation, and classification, alongside Jetson/TensorRT deployment work.
Teaching experience
Teaching Assistant · University of Arkansas
Assisted with Algorithms course slides, homework assignments, and exams.
Teaching Assistant · Master's Computer Vision course · HCMC University of Technology and Education
Prepared course material and instructed graduate Computer Vision practice sessions across image processing, classical/learning-based vision, implementation, and experiment interpretation.
Teaching Assistant · International University — VNU HCMC
Taught undergraduate labs/tutorials in Sensors and Instrumentation, Robotics, and Biosignal Processing.
Technical skills
Applied AI / LLM / agents
LLM/RAG/agents · LangGraph/LangChain orchestration · tool/model routing · code/tool execution · web-search workflows · memory/context management · grounded generation · guardrails · human-review boundaries · evaluation · authority separation
Retrieval & knowledge systems
Qdrant · Milvus · Pinecone · pgvector · embeddings · chunking/metadata strategy · governed ingestion · metadata/permission filtering · exact citations · immutable provenance · retrieval evaluation · retrieval failure handling
Voice / real-time AI
Azure Speech · multilingual ASR/transcription · Vietnamese ASR/TTS · speech evaluation · WebSockets/SSE · real-time conversation state · AsyncIO · background processing
Computer vision / video / edge
YOLO11/YOLOv8 · PyTorch · TensorFlow · OpenCV · Detectron2 · Fast-ALPR · ByteTrack · TensorRT · ONNX Runtime · NVIDIA Jetson · CUDA · RGB-D · MediaMTX · RTSP/HLS · FFmpeg
Quantitative ML & research data
Rust/Python causal core · Point-in-time data · Arrow/PyArrow/Parquet · versioned event stores · global OOF · purge/embargo · multiple-testing controls · Alpha History · LightGBM · CatBoost · XGBoost · Scikit-learn · Polars · DuckDB · SciPy · Statsmodels · Optuna · NautilusTrader
Backend & distributed systems
Python · FastAPI · AsyncIO · REST/SSE · WebSockets · Celery · RabbitMQ · Redis · PostgreSQL · SQLite · MongoDB · MinIO/S3 · retries · idempotency · durable state
Product, browser automation, cloud & delivery
Next.js · React · TypeScript/JavaScript · Open edX · Playwright · browser/tool verification · Docker · Kubernetes · Linux · Windows · systemd · Nginx · AWS · Azure
Languages
English — professional working proficiency · Vietnamese — native
Education
Master of Engineering (MEng) in Computer Engineering · University of Arkansas
GPA 4.0/4.0 · thesis: “Towards Multi-modal Interpretable Video Understanding” · advisor: Prof. Ngan Le · fully funded Ph.D. admission in 2021 followed by endowed graduate scholarships in 2022 and 2023.
Bachelor of Science in Automation and Control Engineering · International University — VNU HCMC
GPA 3.5/4.0 · Top 1% · half-tuition scholarship recipient.
Prior Ph.D.-track research is represented in the University of Arkansas research role above; no completed Ph.D. is claimed.
Selected scholarships & early honors
Rodger S. Kline Chair in Computer Science and Computer Engineering Scholarship
University of Arkansas
Reginald R. “Barney” and Jameson A. Baxter Endowed Graduate Scholarship
University of Arkansas
Fully Funded Ph.D. Admission
University of Arkansas
First Prize · Ba Ria–Vung Tau Informatics Competition
Ba Ria–Vung Tau, Vietnam
First Prize · Ba Ria–Vung Tau Informatics Competition
Ba Ria–Vung Tau, Vietnam
Gold Medal · Vietnam Southern Region Olympic 30/4 — Informatics
Vietnam
Selected publications
CarcassFormer · Poultry Science
Simultaneous localization, segmentation, and classification of poultry carcass defects
AOE-Net · International Journal of Computer Vision
Entity-interaction modeling with adaptive attention for temporal action proposal generation
VLTinT · AAAI
Visual-linguistic Transformer-in-Transformer for coherent video paragraph captioning · AAAI Oral
sCL-ST · IEEE JBHI
Supervised contrastive learning with semantic transformations for multi-lead ECG arrhythmia classification
VLCAP · IEEE ICIP
Vision-language contrastive learning for coherent video paragraph captioning
AEI · BMVC
Actor-environment interaction with adaptive attention for temporal action proposal generation
ABN · IEEE Access
Agent-aware boundary networks for temporal action proposal generation
Multi-module RCNN + Transformer · IEEE BHI
Multi-module recurrent convolutional neural network with Transformer encoder for ECG arrhythmia classification
Source & evidence
The public web résumé follows the current canonical résumé architecture: shared chronology and factual boundaries, plus separate depth layers for Applied AI/LLM systems, Computer Vision/Video AI, Quantitative Research/Trading Systems, and academic research. Public evidence is exposed through case studies, GitHub activity, and Google Scholar; confidential project material, credentials, internal infrastructure labels, patient data, and private trading alpha remain excluded.