I’m a Machine Learning / Computer Vision Engineer focused on building production-grade AI systems — from model development to scalable deployment across edge and cloud environments.

I work at the intersection of Computer Vision, backend systems, and MLOps, with hands-on experience taking AI products from 0 → production → scale in real-world, latency-sensitive systems.

• Object Detection, Segmentation, Tracking
• Real-time vision pipelines for industrial and edge use-cases
• Model optimization for latency, throughput, and accuracy
• CNNs, Transformers, classical + deep CV methods

• End-to-end ML pipelines (data → training → deployment → monitoring)
• Model serving using NVIDIA Triton Inference Server
• Experiment tracking, dataset versioning, and reproducibility
• Production monitoring and observability for ML systems

• Python-based backend services (FastAPI, gRPC)
• Service-to-service communication and API design
• Event-driven and modular system architectures
• Debugging and performance tuning of production systems

• Deployment and monitoring of AI systems on a fleet of 1500+ edge devices
• Hands-on experience with NVIDIA Jetson and Raspberry Pi
• Designing resilient systems for remote and resource-constrained environments

Languages & Frameworks

Backend & APIs

Datastores & Data

MLOps, DevOps & Observability

Edge & Hardware

• B.Tech — Artificial Intelligence & Data Science
• DeepLearning.AI – Machine Learning Specialization
• NVIDIA Certifications
  • Fundamentals of Accelerated Computing with CUDA
  • Building Video AI Applications on Jetson Nano

• Building AI-first products with real-world impact
• ML systems engineering and large-scale deployments
• Computer vision for robotics, security, and industrial automation
• Solving hard engineering problems at the system and infrastructure level

📫 Let’s connect

• LinkedIn: https://linkedin.com/in/raghul-p
• Email: [email protected]