Physical AI & Edge AI Systems Engineer focused on robotics, Jetson-class inference, runtime observability, and AI-native infrastructure.
I build AI systems where models meet physical infrastructure: robots, edge devices, telemetry streams, safety constraints, and operator workflows.
My telecom background gives me depth in distributed systems, latency, wireless infrastructure, and operational reliability. I now apply that foundation to Physical AI, Robotics, Edge AI, and AI-RAN systems.
Core focus: AI systems that can be benchmarked, observed, validated, deployed, audited, and operated safely under real runtime constraints.
These projects define the core architecture of my portfolio: robotics, Jetson-class edge inference, runtime telemetry, safety observability, and deployment-aware AI systems.
| Project | Focus | Signal |
|---|---|---|
| physical-ai-jetson-robotics | Jetson, ROS 2, robotics, sim-to-real | Flagship Physical AI system |
| physical-ai-safety-observability | Safety events, runtime telemetry, observability | Operational AI and safety layer |
| jetson-edge-ai-security | Edge telemetry, anomaly detection, Jetson constraints | Security and reliability at the edge |
These projects translate edge AI, telemetry, and analytics into operator-facing systems with reports, dashboards, and decision support.
| Project | Focus | Signal |
|---|---|---|
| urban-edge-vision-analytics | Edge vision, traffic events, incident reporting | Applied computer vision system |
| private-5g-data-pipeline | Private 5G telemetry, data quality, reporting | Network operations data pipeline |
| wireless-link-intelligence-system | RF link metrics, SINR/RSSI interpretation, dashboarding | Wireless engineering decision support |
These projects connect my telecom background to AI-native infrastructure: neural receivers, 5G/6G link intelligence, RAN telemetry, and edge-aware wireless operations.
| Project | Focus | Signal |
|---|---|---|
| neural-receiver-5g-nr | ML-assisted 5G NR receiver concepts | AI for physical-layer wireless systems |
| ai-ran-kpi-forecasting | RAN KPI forecasting and operational intelligence | AI-RAN operations analytics |
| private-5g-data-pipeline | Private 5G telemetry foundation | Data layer for AI-native network operations |
Current portfolio work is focused on strengthening visible proof across the flagship systems:
- physical-ai-jetson-robotics — Jetson/runtime evidence, ROS 2 workflows, telemetry artifacts, and sim-to-real validation
- physical-ai-safety-observability — safety event evidence, operator review flow, runtime metrics, and observability reports
- jetson-edge-ai-security — defensive telemetry replay, anomaly alerts, edge security reporting, and Jetson-oriented constraints
Hiring-manager mapping: HIRING_MANAGER_BRIEF.md.
This portfolio separates implemented workflows, runnable scaffolds, mock validation paths, planned hardware benchmarks, and future deployment targets.
Mock adapters, synthetic inputs, and planned Jetson paths are useful engineering scaffolds, but they are not claimed as real-world deployment proof until evidence artifacts exist.
Physical AI / Robotics: ROS 2, MoveIt 2, Isaac Sim, Isaac Lab, OpenUSD
Edge AI: NVIDIA Jetson, TensorRT, ONNX, CUDA, vLLM, VLM/LLM deployment
Runtime Observability: telemetry pipelines, safety events, operational metrics, evidence artifacts
AI / ML: Python, PyTorch, scikit-learn, XGBoost, SHAP, MLflow
Operational AI / RAG: retrieval-grounded copilots, local inference workflows, guardrails, human review
Data / Infrastructure: SQL, Spark, Airflow, dbt, Docker, Kubernetes, CI/CD
AI-RAN / Wireless: RAN telemetry, KPI forecasting, neural receiver concepts, private 5G, wireless link analysis
Cloud / Distributed Systems: AWS, Azure, GCP, Terraform
- Email: obiedeh@gmail.com
- LinkedIn: linkedin.com/in/obinna-edeh-206306137
- GitHub: github.com/obiedeh