Vision on real hardware
Visual perception, sensor fusion and recovery policies on constrained edge hardware, flown rather than simulated.
MACHINE LEARNING ENGINEER/VIENNA
COMPUTER VISION · AUTONOMOUS SYSTEMS
I build ML systems thatwork outside the lab.
Since 2021 I've led perception and navigation for a drone platform: classical vision, monocular depth, deep learning and sensor fusion under real-time, GPS-denied constraints.
Also: applied LLM document intelligence and physics-informed neural networks.
NAVEEN RAJANML ENGINEER
01WHAT I BRING
Document intelligence
Entity extraction and resolution, with evaluation and reviewable outputs, for legal-style unstructured corpora.
Physics-informed models
Reproducible PINN experimentation: one model covering a family of under-determined industrial simulations.
02SELECTED WORK
Built, tested, learned.
ROBOTICS · EDGE ML
Autonomous perception & navigation
Led perception and navigation for a drone platform, combining classical computer vision, monocular depth, deep learning, sensor fusion, and recovery policies for GPS-denied operation.
97%reported navigation robustness after recovery-policy improvements
SCIENTIFIC ML
PINN research framework
A configurable experimentation framework for physics-informed neural networks, with reusable problem abstractions, CLI orchestration, and reproducible training workflows.
APPLIED AI
Entity resolution
An AI-assisted document processing project exploring entity extraction, normalization, evaluation, and reviewable structured outputs.
03GET IN TOUCH
Hiring for CV or ML? Let's talk.
I'm looking for a full-time role on a team building technically ambitious products. The fastest way to reach me ishello@navrjn.com.