Nvidia Isaac & Jetson Mentor
Budget: ₹20,000 – ₹30,000 INR
I’m ready to dive into Nvidia’s robotics stack—Isaac Sim, Isaac Lab, and the Jetson family—but I need someone who can guide me from square one. My immediate focus is the Jetson Orin Nano, yet I eventually want to branch out to AGX and even Thor once the fundamentals are solid.
My background: I’m a beginner in both robotics and AI, so please be comfortable breaking complex ideas into clear, practical steps. I learn best through hands-on, one-on-one sessions conducted online. We can screen-share inside Isaac Sim, walk through Python scripts, and iterate on small projects that culminate in a functioning robot pipeline—from simulation to deployment on the Orin Nano board.
Key areas I’d like to cover:
• Setting up Isaac Sim and Isaac Lab environments (Ubuntu, ROS 2, Omniverse).
• Building, training, and testing perception models in simulation.
• Transferring those models to real hardware and optimizing them for Jetson.
• Best practices for CUDA acceleration, TensorRT, and power management on Orin Nano.
• Road-mapping steps to scale the same workflow to AGX and Thor in the future.
Deliverable: a structured learning path supplemented by live sessions, example code, and working demos that run on my Jetson Orin Nano. If you’ve successfully shipped robots or AI applications on Nvidia hardware, I’d love to hear how you can help me achieve the same.
My background: I’m a beginner in both robotics and AI, so please be comfortable breaking complex ideas into clear, practical steps. I learn best through hands-on, one-on-one sessions conducted online. We can screen-share inside Isaac Sim, walk through Python scripts, and iterate on small projects that culminate in a functioning robot pipeline—from simulation to deployment on the Orin Nano board.
Key areas I’d like to cover:
• Setting up Isaac Sim and Isaac Lab environments (Ubuntu, ROS 2, Omniverse).
• Building, training, and testing perception models in simulation.
• Transferring those models to real hardware and optimizing them for Jetson.
• Best practices for CUDA acceleration, TensorRT, and power management on Orin Nano.
• Road-mapping steps to scale the same workflow to AGX and Thor in the future.
Deliverable: a structured learning path supplemented by live sessions, example code, and working demos that run on my Jetson Orin Nano. If you’ve successfully shipped robots or AI applications on Nvidia hardware, I’d love to hear how you can help me achieve the same.
Related categories:
Python
CUDA
Machine Learning (ML)
Robotics
Embedded Systems
Deep Learning
Simulation
AI Development