Thein Kyaw Lwin
AI/ML Engineer · Data Scientist · Edge AI for agriculture, public health, and low-connectivity environments
Thein Kyaw Lwin is an AI/ML practitioner and data scientist with 7+ years of field-embedded technology experience across precision agriculture, public health, and enterprise IT. He builds practical AI systems from raw field data through production deployment, with a focus on edge AI, computer vision, generative AI, and data systems for resource-constrained environments.
He is actively applying for AI/ML Engineer, Data Scientist, AI Engineer, AgTech, ICT4D, and mission-aligned technology roles in Southeast Asia, Singapore, Australia/New Zealand, and remote teams.
Selected proof points
- Designed a hybrid lightweight CNN for chickpea disease detection, achieving 82.09% cross-domain accuracy at 0.870 MB, validated on 115 real Android devices via Google AI Edge Portal.
- Built and deployed Shwe Taungthuu, a Gemini 2.5 Flash bilingual agricultural advisory agent on Google Cloud Run, with Burmese voice/text input for Myanmar farmers.
- Built A2C Myanmar Address-to-Coordinates, a transformer-based geospatial NLP system trained on 610,509 Myanmar addresses with a live Streamlit map demo.
- Supported national-scale health data infrastructure at WHO Myanmar, including DHIS2/OpenMRS systems for 1,000+ users with 99.99% uptime.
- Built ICT-enabled agricultural data workflows at CESVI Myanmar reaching 130 villages and 26,234 households, with farmer training for 2,000+ users.
Featured work
- Chickpea Fusarium Wilt Detector — offline Android edge-AI plant disease detection for smallholder farmers.
- Shwe Taungthuu — bilingual Gemini agricultural advisory agent on Google Cloud Run.
- A2C Myanmar Address-to-Coordinates — transformer-based geospatial NLP for Myanmar address geocoding.
- MMDT Intro to Deep Learning Projects — applied deep-learning coursework spanning tabular regression, NLP classification, and CNN benchmarking.
- ML Algorithms from Scratch — classical ML implementations in NumPy with derivations and validation.
Core stack
Python · PyTorch · TensorFlow/Keras · Scikit-learn · FastAPI · Vertex AI · Gemini API · Google Cloud Run · Kotlin · Jetpack Compose · TFLite/LiteRT · SQL · Power BI · QGIS · Docker · Linux
For role-specific context, see the CV, project portfolio, GitHub, or LinkedIn.