I focus on building cutting-edge AI systems across multiple domains, from intelligent agents to advanced computer vision solutions:
🤖 Large Language Models & Multi-Agent Systems
- Architecting LLM and VLLM-powered multi-agent systems with RAG pipelines
- Building deep search frameworks with browser automation for web intelligence
- Developing agentic workflows for brand analysis, customer intelligence, and product surveillance
- Implementing vector search solutions with Qdrant for brand protection and identity linking
- Creating custom benchmarking pipelines for model evaluation
👁️ Computer Vision & Perception
- Designing & building custom object detection, classification, segmentation, and instance segmentation models
- Building medical imaging systems for pathology analysis
- Developing autonomous vehicle mapping and perception solutions
- Creating mathematical and photogrammetric algorithms for real-world coordinate transformation
- Deploying edge AI solutions on embedded systems (Raspberry Pi, Jetson Nano)
- Building automated annotation pipelines and dataset curation workflows
🔬 Currently Exploring
- Advanced agentic architectures and multi-agent orchestration
- Vision-language models (VLLMs) for multimodal understanding
- Vector search optimization for large-scale similarity problems
- Real-time inference optimization on edge devices
- SLAM, SFM, and NeRF techniques for 3D reconstruction
Languages
AI/ML Frameworks & Libraries
Computer Vision Tools
LLM & Agent Frameworks
Vector Databases & Search
MLOps & Deployment
Data & Message Queues
Cloud Platforms & Services
Annotation & Visualization
Hardware & Edge
Open to collaborations and interesting challenges in AI/ML