Tuan Quang

Software Engineer, Applied AI in production

About Me

Senior AI Engineer with 7+ years building and optimizing production AI systems in financial services, including LLM inference, multi-agent workflows, vector search, guardrails, and evaluation on AWS and GCP. Proven record of cutting inference cost and latency through quantization and model optimization while leading engineers through architecture and design reviews.

My core strengths include:

• Core — LangGraph, LangChain, PyTorch, AWS Bedrock/SageMaker, FAISS, Neo4j, FastAPI, Docker, Kubernetes, Terraform
• LLM & AI Systems — CrewAI, AutoGen, LlamaIndex, RAG (Agentic/Corrective/Self-RAG), Prompt Engineering, Function Calling/Tool Use, Structured Output, Guardrails, LLM Evaluation, MCP Server
• ML & Deep Learning — TensorFlow, JAX, Hugging Face (Transformers, PEFT, Accelerate), Scikit-learn, OpenCV, Fine-tuning (QLoRA/LoRA), Quantization (GPTQ/AWQ/GGUF), ONNX, W&B, MLflow
• Data & Infrastructure — Pinecone, Chroma, Weaviate, PostgreSQL, MongoDB, DynamoDB, Kafka, PySpark, Airflow, DVC, Feast, OpenTelemetry, Grafana, Prometheus, GitHub Actions, CI/CD
• Languages — Python (Proficient), Java, JavaScript/TypeScript, SQL, C++, C#Galileo Financial Technologies