Dr. Farshid PirahanSiah
Embedded Computer Vision
& Edge AI at Scale
I help businesses turn computer vision research into production-ready embedded applications. From model optimization to multi-camera deployment on NVIDIA Jetson, Raspberry Pi, Hailo, Axelera, and beyond.
Let's Talk on LinkedInEmbedded Computer Vision
Real-time object detection, tracking, and classification on edge devices. From prototype to production deployment on Jetson, Coral, Hailo, and Axelera accelerators.
Model Optimization & Quantization
INT8/FP16 quantization, pruning, and knowledge distillation. Reduce model size 4-10x while maintaining accuracy for real-time inference on resource-constrained hardware.
Multi-Camera Systems
Synchronized multi-camera setups for 3D reconstruction, stereo vision, and surveillance. Scaling from 2 to 100+ cameras with GStreamer and GPU-accelerated pipelines.
LLM & AI Integration
Integrate vision-LLMs, RAG pipelines, and multi-agent systems into CV workflows. Local inference with Ollama, or cloud APIs for production-scale AI applications.
MLOps & CI/CD
End-to-end ML pipelines: data collection, training, evaluation, deployment, and monitoring. Docker, Kubernetes, MLflow, and automated model versioning.
Hardware Selection & Prototyping
Evaluate and select the right AI accelerators for your use case. NVIDIA Jetson, Intel NPU, Hailo-15, Axelera Metis, Google Coral, FPGA, or custom solutions.
Technical Deep Dives
Ready to Scale Your CV Application?
Whether you need to optimize a model for edge deployment, build a multi-camera pipeline, or integrate AI into your product — I can help.
Connect on LinkedIn