I build vision and language systems that actually ship — from real-time object detection on the edge to grounded RAG agents.
- 🔬 AI Researcher working across Computer Vision and Neural Networks, affiliated with PIAIC.
- 👁️ I build real-time vision systems — object detection & tracking (YOLOv8/v11, ByteTrack/DeepSORT), self-supervised representation learning (DINOv2), OCR, and edge deployment (TensorRT / ONNX / Jetson).
- 🗣️ On the language side I build RAG pipelines, Autonomous Agents, and LLM apps — NL-to-SQL, grounded document QA, local/private LLMs, Distillation and fine-tuning.
- 🎮 I design reinforcement-learning environments — e.g. multi-step organic-reaction product prediction — framing real problems as RL tasks (states, actions, reward shaping).
- ⚙️ I care about the boring parts that make AI real: latency, FPS, quantization, containerization, and reproducibility.
- 💬 Ask me about YOLO26, DINOv2, RF_DETR, ONNX, TensorRT on Jetson, Arm Cortex SOCs or building production RAG Pipelines.
| Project | What it is | Stack |
|---|---|---|
| 🧪 Chemistry-RL | Reinforcement-learning environment for multi-step organic-reaction product prediction | RL · Gym-style env · Python |
| 🍕 pizza-check-cv | Production CV platform for real-time pizza quality control | YOLOv11 · FastAPI · Electron · MaixSense RGB-D |
| 🦅 hawkeye-lite | Real-time aerial detection & tracking with Jetson-ready edge deployment | YOLOv8 · ByteTrack · TensorRT |
| 📄 AWS-BEDROCK-QA-AGENT | Document QA agent with NL-to-SQL over a data lake | AWS Bedrock · Athena · Glue · Parquet |
| 🧬 DinoV2_Meta_VLM | DINOv2 as a backbone — benchmarking CNNs vs. self-supervised attention | DINOv2 · PyTorch · VLM |
| 🔎 RAG with ReAct | Advanced RAG with query reformulation + ReAct multi-step reasoning | LangChain · RAG · ReAct |
| 🏃 3d-pose-ronaldo | 3D human pose estimation — skeleton tracking, 3D bounding boxes, body orientation | YOLOv8-Pose · ByteTrack · NumPy |
Detection & Tracking ▸ YOLOv8 / YOLOv11 / YOLOv3-v5 · ByteTrack · DeepSORT
Representation Learning ▸ DINOv2 (self-supervised) · CNN vs. VLM benchmarking
OCR & Document AI ▸ CRNN · CRAFT / keras-ocr · docTR · MNIST/handwriting
Edge & Optimization ▸ NVIDIA Jetson · TensorRT · ONNX · OpenVINO · TFLite
Applied CV ▸ Quality control · aerial/satellite · anomaly detection · RGB-D
- 🎯 Real-time object detection + multi-object tracking with persistent IDs and event/zone alerting.
- 🧠 Self-supervised vision with DINOv2 — using foundation-model backbones for downstream classification and measuring efficiency vs. classic CNNs.
- ⚡ Edge deployment: exporting models to TensorRT/ONNX and hitting real-time FPS on constrained hardware like the Jetson Orin NX.
RAG & Retrieval ▸ Advanced RAG · ReAct agents · query reformulation · grounded QA
LLM Apps ▸ NL-to-SQL · document QA · local/private LLMs (Qwen) · knowledge bases
Agents ▸ LangChain · LangGraph · tool-use & multi-step reasoning
Fine-tuning ▸ LoRA / efficient fine-tuning of LLMs & VLMs
Classic NLP ▸ Text classification · sentiment analysis (IMDB) · embeddings
- 🔎 Built multiple RAG systems — from cloud (AWS Bedrock + Athena NL-to-SQL) to fully local, private pipelines with no data leaving the machine.
- 🤖 Experience with agentic patterns (ReAct, LangGraph) for multi-step reasoning and tool use.
- 📝 Foundations in classic NLP — sentiment classification, embeddings, and sequence models.
Environments ▸ custom Gym-style envs · multi-step decision tasks · reward shaping
Applied RL ▸ organic-reaction product prediction (Chemistry-RL)
Agents ▸ policy/agent training loops · RL for LLM/agent fine-tuning (GRPO-style)
Search ▸ Monte-Carlo Tree Search for sequential decision making
- 🧪 Built a custom RL environment that frames multi-step organic-reaction prediction as a sequential decision problem — designing the state/action space and reward.
- 🤖 Comfortable connecting RL to modern agents — reward-driven fine-tuning of LLM/VLM agents and tree-search planning.
⚡ Always exploring the frontier where vision and language models meet the real world.