Looking for a job

Rahul Adidravid

@rahuladidravid

Message

Computer Vision Engineer | Edge AI & Vision Systems | Real-Time Video Intelligence

India

Message

What I'm looking for

I’m looking for a role where I can build and deploy real-time, low-latency computer vision systems for production and edge. I want to pair strong inference optimization with GenAI (LLMs/RAG) to ship multimodal, business-ready AI.

I’m a Computer Vision Engineer specializing in real-time AI video analytics and edge deployment. Over the last 3 years, I’ve built systems that help companies reduce manual monitoring, improve safety, and automate operations. I’ve deployed multi-stream inference pipelines on NVIDIA Jetson devices and cloud platforms, delivering scalable and low-latency AI solutions.
I’m passionate about turning AI research into real-world impact, and I’m looking for opportunities to build high-value systems for companies seeking efficiency, automation, and actionable intelligence.”

Project & Domain Expertise

• Human activity and behavior monitoring
• Workplace safety and PPE compliance systems
• Crowd flow and occupancy analytics
• Restricted zone and intrusion detection
• Warehouse operations and safety monitoring

I’m open to opportunities where I can contribute to building scalable, real-time vision AI systems for practical, high-impact applications.

Experience

Work history, roles, and key accomplishments

Current

Computer Vision Engineer

Current

Mentoroid Pte. Ltd

Dec 2024 - Present (1 year 6 months)

Develop and maintain real-time computer vision and video analytics solutions, designing scalable architectures and optimizing inference workflows for production use. Collaborate with research, backend, and deployment teams to integrate AI models into stable systems and support evaluations for new AI capabilities.

Video Analytics Object Detection NVIDIA Jetson Triton Inference Server TensorRT Onnx Docker fastAPI

Junior Computer Vision Engineer

Agrex.ai

Oct 2023 - Dec 2024 (1 year 2 months)

Designed and deployed low-resource AI video analytics pipelines using Triton Inference Server and FastAPI, including a low-cost setup capable of handling 200 streams on a single device. Delivered YOLO (v5–v8) detection pipelines across edge devices and servers, achieving 95%+ accuracy across projects.

Triton Inference Server fastAPI YOLO V5 V8 Object Detection Docker REST APIs

AI/ML Intern

VMukti Solutions Pvt. Ltd

Sep 2022 - Mar 2023 (6 months)

Built a YOLO-based object detection model for real-time video analysis using Python and TensorFlow. Fine-tuned YOLOv5 on a custom dataset using transfer learning from a pre-trained model.