Kaung Myat

AI Engineer with 8 years of experience building production GenAI and AI agentic systems across RAG, PyTorch fine-tuning, vLLM serving, and MLOps.

AI / ML Stack


Experience


Lead AI Engineer

Jan 2024 — Present

APS Asia PDA Enterprise · Rockville, MD

  • Designed and shipped production GenAI and multi-agent systems with Python, PyTorch, LangChain/LangGraph, AWS Bedrock, MCP, A2A, FastAPI, and RAG architectures, improving LLM application reliability and response quality by 28%.
  • Architected high-throughput LLM inference on AWS EKS with vLLM, KV caching, quantization, FlashAttention, continuous batching, and speculative decoding, cutting inference latency and serving costs by 68%.
  • Fine-tuned transformer LLMs with LoRA/PEFT adapters on domain-specific datasets, improving task accuracy by 15% while reducing fine-tuning compute by 70%.
  • Hardened LLM applications with prompt-injection detection, input/output sanitization, guardrails, PII filtering, and tool-access policies, reducing unsafe or unauthorized model interactions by 30%.
  • Built MLOps/LLMOps pipelines covering CI/CD for model and prompt versioning, automated evaluation, and OpenTelemetry with LangSmith tracing, improving production observability and debugging efficiency by 25%.
  • Designed semantic-search infrastructure on embedding models, FAISS, ChromaDB, and OpenSearch for low-latency retrieval over large unstructured datasets.

Senior Machine Learning Engineer

Jan 2017 — Jul 2022

APS Asia PDA Enterprise · Rockville, MD

  • Engineered real-time personalized recommendation systems with TensorFlow, two-tower retrieval, sequence modeling, and Graph Neural Networks, improving recommendation relevance by 30% and user engagement by 43%.
  • Developed computer vision models with YOLO and DenseNet for image detection and classification, improving accuracy by 20% and reducing inference time by 25%, and built OCR and document-processing pipelines that cut manual processing time by 30%.
  • Led cross-functional engineering and product teams through the end-to-end AI/ML development lifecycle, driving technical decisions, architecture alignment, and delivery of production capabilities in a fast-paced Agile environment.

Recent Blogs


Contact


Reach me out via