Portfolio · AI Handbook · Email
I'm an AI Engineer building applied AI systems across generative AI, computer vision, and machine learning.
I work on RAG and multi-agent workflows, detection, segmentation, and OCR pipelines, as well as the backend and MLOps infrastructure needed to train, evaluate, and deploy AI systems.
Beyond implementation, I'm interested in how intelligent systems are designed, evaluated, and improved over time. I also enjoy documenting what I learn and sharing technical insights with the developer community.
- Core Languages & Data: Python · SQL · R · NumPy · pandas · Jupyter Notebook
- Generative AI & LLM Systems: RAG · Agent Orchestration · Multi-Agent Workflows · Embeddings · Vector Search · Prompt Design · Tool / Function Calling · Structured Outputs · LLM Evaluation · Guardrails · Google Gemini · AWS Bedrock
- Machine Learning: scikit-learn · XGBoost · Random Forest · Feature Engineering · Model Evaluation · SHAP · MLflow
- Deep Learning & Computer Vision: PyTorch · TensorFlow · YOLO · PaddleDetection · PaddleSeg · SAM2 · PaddleOCR · OpenCV · Detection · Segmentation · Keypoints · OCR · ONNX
- Robotics & Edge AI: ROS2 · Sensor Fusion · ArUco / AprilTag · solvePnP · MAVROS · Jetson Nano
- AI Backend & Data Infrastructure: FastAPI · Django · REST APIs · PostgreSQL · MySQL · SQL Server · Redis · OpenSearch · ChromaDB · Data Pipelines · ETL
- MLOps, Cloud & Deployment: Docker · Ray · AWS SageMaker · ECS / ECR · S3 · Celery / SQS · GitLab CI/CD · Linux
I document what I learn about AI systems, machine learning, computer vision, and practical engineering in my AI Handbook.
I'm always happy to connect with people interested in AI, software engineering, and building useful technology.