# Dr. Farshid Pirahansiah
## Computer Vision & AI
### 3D Vision
- Multi-Camera Systems
- Optical Flow
- Point Clouds
### AI & LLMs
- RAG
- Multimodal
- Agents
## CUDA & GPU
- Numba JIT
- PyCUDA
- MLX / CoreML
## Programming
- C++ Quick Ref
- Python Config
- Shell & Vim
## Optimization
- Quantization
- Pruning
- Edge AI
## Career
- Startup Guide
- 3 Patents
- 17+ Papers
Dr. Farshid Pirahansiah
| Computer Vision Research Engineer & Technical Lead | Berlin, Germany |
About Me
I am an accomplished Research Engineer with 12+ years of experience, including a PhD in Computer Science. My career has been dedicated to Computer Vision, Machine Learning, and ML Operations, with a proven track record of transforming complex algorithms into production-ready applications.
Experience
- 12+ years: Computer Vision, C++, R&D
- 10+ years: Machine Learning, Deep Learning, Python, Embedded Systems, Multi-Camera Systems
- 7+ years: IoT, Model Optimization, Robotics, Medical Imaging, Cloud (AWS)
- 5+ years: Technical Lead, Global Collaboration
- 2+ years: LLMs, Multimodal AI, RAG, Agentic Workflows
Core Skills
- Computer Vision & AI: Image processing, deep learning, real-time systems
- Languages: Python, C++, MATLAB
- Frameworks: PyTorch, TensorFlow, ONNX Runtime, TensorRT, OpenVINO
- Tools: Docker, Kubernetes, AWS, Git, MLflow, CI/CD
- Edge AI: Jetson, Coral TPU, model quantization (INT8/FP16)
Published Research
- 3 Patents (Face Image Augmentation, Vehicle Detection, Facial Analysis Advertising)
- 2 Book Chapters (Springer)
-
6 Journal Papers 11 Conference Papers - Full Portfolio
Consulting Services
I offer personalized coaching, tutoring, and consulting in computer vision and AI. Learn more.
Content Hub
Computer Vision & 3D
- 3D Vision & Multi-Camera Systems — Point clouds, depth sensing, camera sync
- Optical Flow: Challenges & Solutions — Illumination, occlusion, fast motion
- Real-Time Multi-Camera Systems — Scaling to 100+ cameras
AI & LLMs
- Advanced LLM Concepts — RAG, embeddings, multimodal
- Orchestrating AI Agents — Multi-agent systems
- Blog: AI & LLMs — RAG vs CAG, multi-agent architectures
CUDA & GPU
- Numba JIT Tutorial — Python performance optimization
- PyCUDA Kernel Explanation — CUDA from Python
- CUDA in VS Code on Windows — Dev environment setup
- MLX, CoreML & Metal — Apple Silicon ML
Programming & Tools
- C++ Quick Reference — Memory, STL, debugging
- Python Configuration & Tips — Config management, pybind11, Cython
- Developer Tools & Setup — Docker, GitHub, CLI tools
- Shell & Vim Reference — Terminal essentials
Optimization & ML
- CV, DL & ML Optimization — Quantization, pruning, frameworks
- Prompt Engineering Templates — LLM prompt patterns
Business & Career
- Startup Guide — Edge AI business, fundraising, pitch decks
- SEO for LLM-Powered Search — Structured data, AI visibility
- Local Video Avatar Generator — Ollama + Wav2Lip tutorial
- Top LinkedIn Posts 2024 — Camera calibration, C++, robotics
Resources
- Portfolio & Publications — Patents, books, papers
- Curated Links — Tools, tutorials, reading
Connect
AI Assistant
- Computer Vision Developer GPT — Expert in Python, OpenCV for CV applications