Available for freelance & full-time opportunities

Hi, I'm Nikhil Rathore

|

I build production-grade computer vision systems — from real-time face recognition at 70 lakh+ identity scale to person re-identification models running on Raspberry Pi at the edge. 4+ years turning research into deployed, reliable AI.

Nikhil Rathore
Face Match 99.7% ID #70,00,214 FPS: 30

Turning research into real-world AI

I'm a Computer Vision & AI Engineer at Magellanic Cloud Ltd (previously IVIS International), building real-time video analytics systems used across banking, retail and surveillance deployments in production.

My work spans the full pipeline: training deep learning models, optimizing them with quantization (PTQ/QAT) and hardware acceleration (TensorRT, OpenVINO), and deploying them on everything from NVIDIA GPUs to ARM edge devices like the Raspberry Pi 5 — without sacrificing accuracy or latency.

I care about shipping AI that actually works in the field: fewer false alerts, faster inference, and systems that hold up across 100+ live site cameras.

Hyderabad, India
Software Engineer — CV & AI
MCA, NIT Warangal
0
Years of Experience
0
Faces at Recognition Scale
0
Live Site Cameras Supported
0
AI Models Shipped

Skills & Technologies

Languages

PythonJava C++JNI

Deep Learning

PyTorchTensorFlow KerasHuggingFace

Computer Vision

OpenCVPerson Re-ID Multi-Object TrackingFace Recognition Pose EstimationObject Detection Segmentation

Optimization & Acceleration

ONNXOpenVINO (FP32/INT8) TensorRTCUDA PTQQAT Latency Profiling

Edge Deployment

NVIDIA GPUsIntel CPUs ARM / Raspberry Pi 5Embedded Targets

Infrastructure

DockerLinux GitAWS EC2 FlaskFastAPI

Work Experience

Software Engineer — Computer Vision & AI

Magellanic Cloud Ltd, Hyderabad

Sept 2021 — Present
  • Joined IVIS International Pvt Ltd in Sept 2021; transferred to parent company Magellanic Cloud Ltd in Oct 2024, continuing in the AI/ML Engineer role.
  • Developed real-time face recognition, people tracking, and frisking-compliance systems using deep learning and image processing.
  • Built and optimized sample apps/POCs across Python, C++, and Java for testing and deployment.
  • Integrated C++ inference logic with Java applications via JNI for fast, scalable backend processing.
  • Designed internal tools for automated video-clip handling, model inference, and system health checks.
  • Reduced false alerts in video analytics while maintaining rule-based logic across 100+ site cameras.
  • Led client dashboard improvements — tracking daily events and producing monthly accuracy reports.

Software Developer Intern

IVIS International Private Limited, Hyderabad

Feb 2021 — Aug 2021
  • Selected through campus placement for a technical internship during the final semester.
  • Worked on an attire-classification deep learning model.

Featured Projects

Banking Face Recognition at Scale

Real-time customer identification from live CCTV across 70 lakh+ enrolled identities using ArcFace + RetinaFace, with HNSW approximate nearest-neighbor search and TensorRT inference. Delivered as a C++/JNI library for Java banking applications.

ArcFaceTensorRTHNSWJNI

Person Re-ID + Edge Tracker

Trained a ResNet-50 + ArcFace head with Batch-Hard Triplet Loss from scratch, quantized to INT8, and deployed live at 4 FPS on Raspberry Pi across bank and retail sites via OpenVINO.

PyTorchOpenVINO INT8Raspberry Pi

Automated Frisking Compliance

A novel, from-scratch keypoint-based system that measures coverage between guard hands and employee body keypoints to flag incomplete security frisking (<90%) in real time, replacing manual CCTV review.

Pose EstimationOpenCVRule Engine

Modular CCTV Intelligence Platform

Productizing surveillance AI as deployable microservices: RTSP ingestion → YOLOv8 detection → Redis state → FastAPI → WebSocket dashboard, deployed on AWS.

YOLOv8FastAPIRedisAWS
View Repo

Gate-Level People Counter

Object tracking and re-identification pipeline for accurate gate-level people counting, with real-time event visualization through a lightweight web client.

TrackingRe-IDWeb Client

AI Inference Monitoring Tool

A web tool to run and monitor AI inference on server-side video data, with interactive selection of models, classes, sites, and date ranges.

FlaskDashboardVideo Analytics

Face Quality Model

A dedicated model to filter good vs. bad quality face captures at registration time, boosting downstream face-recognition accuracy.

CNNQuality Filtering

Int8 Person-Vehicle Motion Detection

Custom motion-triggered object detection built on a quantized Int8 IR person-vehicle model for efficient, always-on site monitoring.

INT8 IROpenVINOMotion Detection

Site Analytics Suite

Camera tampering detection, gender detection, vehicle detection, weapon detection, object color prediction, no-video detection, image quality enhancement, and staff detection — shipped across live customer sites.

Detection ModelsImage Processing

Education & Achievements

National Institute of Technology, Warangal

Master of Computer Application · July 2018 – June 2021

Operating Systems, Data Structures, Analysis of Algorithms, Artificial Intelligence, Machine Learning, Networking, Databases

Achievements

  • 256 AIR — NIMCET MCA Entrance Exam (2018)
  • 27 AIR — VIT MCA Entrance Exam (2018)
  • Certified in Problem Solving by HackerRank

Let's Build Something Together

Have a project, role, or idea in mind? My inbox is open — I usually reply within a day.