1. HELLA GmbH & Co. KGaA (FORVIA HELLA)

   AI Research Intern

   Lippstadt, Germany Aug 2023 – Feb 2024 ▼

   • Worked on the AHEAD (Adaptive Headlights for Enhanced Environment Perception) project to improve night-time perception for automated driving.
   • Adapted and fine-tuned YOLOv8 for glare-robust headlight perception, achieving +30% mAP improvement under adverse illumination.
   • Built a modular multi-task perception pipeline combining detection, segmentation, tracking, and depth estimation for holistic night-time scene understanding.
   • Experimented with ORB/SIFT and integrated Deep SORT for multi-object tracking, improving temporal consistency and ID retention.
   • Conducted robustness/uncertainty analysis under sensor noise, weather variation, and motion blur.
   • Developed multi-camera calibration and QA tools ensuring accurate intrinsic/extrinsic alignment.
   • Collaborated with optics, software, and embedded teams to validate perception components in prototype tests.

   Tech: YOLOv8, PyTorch, OpenCV, ONNX Runtime, DeepSORT, Stereo Calibration, Homography, Triangulation, Python

2. HELLA GmbH & Co. KGaA (FORVIA HELLA)

   Master’s Thesis Researcher

   Lippstadt, Germany Mar 2024 – Nov 2024 ▼

   • Developed a lightweight stereo CNN for dense depth estimation and 3-D object localization, achieving ≈ 3% D1-all error against KITTI + laser ground truth.
   • Generated a synthetic stereo dataset (~9,000 pairs) in Unreal Engine 5 with calibrated intrinsics and low-light scenes.
   • Applied domain randomization (weather, glare, motion blur) and fine-tuned on limited real data, reducing domain gap by ≈ 18% in disparity MAE.
   • Built a full perception pipeline covering training, stereo calibration, QA benchmarking, and uncertainty calibration.
   • Exported and validated ONNX on in-vehicle GPU hardware (< 70 ms latency) with embedded & optics teams.
   • Authored internal technical reports enabling uncertainty-aware perception for adaptive lighting.

   Tech: YOLOv8, PyTorch (Stereo CNN, Cost-Volume Fusion), Unreal Engine 5, OpenCV, NumPy, Docker, ONNX Runtime

3. Indpro Electronic Systems Private Limited

   Automation Engineer

   Pune, India May 2019 – Mar 2020 ▼

   • Developed and deployed PLC control logic (ABB AC800M) for sugar-industry automation systems.
   • Designed HMI dashboards and supported on-site commissioning and troubleshooting across multiple facilities.

   Tech: ABB AC800M PLC, PLC Programming, HMI (SCADA), Industrial Automation

Browse My Recent

Projects

Custom YOLO for Robotic Bin Picking

Developed a custom YOLO model for detecting objects in bin picking tasks, achieving 95% precision in orientation detection.

TensorFlowYOLOBin PickingBlender OpenCVMatplotlib

• Developed TensorFlow-based YOLO model for precise object detection & orientation estimation.
• Trained the model using synthetic (Blender) & real-world datasets, achieving 98% precision.
• Optimized the model to enhance AI performance under industrial conditions, ensuring reliable automation.

Github More Details

Deep Stereo Vision for Nighttime Driving Scenes

Designed a CNN-based depth estimation model using PyTorch, achieving 95% accuracy in low-light scenarios.

PyTorchUnreal Engine 5 MATLABOpenCVStereo Depth

• Designed a CNN-based depth estimation model using PyTorch, for low-light scenarios.
• Generated synthetic training datasets using Unreal Engine 5, improving model generalization.
• Achieved 95% accuracy in depth estimation, outperforming conventional automotive AI methods

Github More Details

3D Reconstruction with Gaussian Splatting

Converted monocular smartphone video into a dense 3D scene using COLMAP preprocessing and Gaussian Splatting rendering.

COLMAPWSLSupersplatGaussian SplattingOpen3D

• Extracted camera poses and sparse point clouds using COLMAP from monocular input video.
• Used Gaussian Splatting to render photorealistic 3D views with transparency and shading effects.
• Visualized and explored outputs in Open3D, and investigated mesh conversion workflows.
• Handled lighting, occlusion, and splat shaders for high-fidelity rendering of complex indoor scenes.

Github More Details

Object Instance segmentation with FastAPI and AWS

YOLOv11 instance segmentation deployed via FastAPI, containerized with Docker on AWS EC2/ECR, and automated using GitHub Actions CI/CD.

YOLOAWSDockerCI/CDFastAPISegmentation

• Real-Time Object Detection & Segmentation: Uses YOLOv11 for accurate instance segmentation.
• FastAPI Backend: Serves the model predictions via REST API.
• User-Friendly Web Interface: Allows users to upload images and view detected objects.
• Dockerized & Cloud-Hosted: Containerized using Docker, pushed to AWS ECR, and deployed on AWS EC2.
• Automated CI/CD Pipeline: Uses GitHub Actions for continuous deployment.
(live demo may not work because of EC2 instance being overused)

Live Demo

Github More Details

PaDiM-based Anomaly Detection

Built a lightweight visual anomaly detection system using PaDiM and ONNX for industrial defect detection.

ONNX RuntimeAnomaly DetectionONNX MatplotlibMobileNetV3

• Extracted multi-level features from MobileNetV3 and computed Mahalanobis-based anomaly scores at pixel level.
• Exported the feature extractor to ONNX and performed inference using ONNX Runtime for cross-platform compatibility.
• Visualized anomalies with heatmaps and binary masks using images from the MVTec AD dataset.

Github More Details

U-Net for Biological Image Segmentation

Trained a U-Net model on fluorescence microscopy images to segment nuclei structures with high accuracy.

ColabPyTorchSegmentation Matplotlib

• Parsed and preprocessed instance masks into binary labels using CLAHE and Gaussian blur.
• Built a lightweight U-Net in PyTorch; trained for 100 epochs on nuclei segmentation dataset.
• Achieved Dice score of 0.89 and IoU of 0.82 on the validation set.
• Visualized predicted masks and prepared inference-ready model using Colab.

Github More Details

Conversational AI Chatbot with RAG & LLM Fine-Tuning

Developed a GPT-based conversational AI assistant, integrated FAISS vector search, and deployed using Docker & Hugging Face Spaces.

Hugging Face / TransformersFAISSRAG

Github Live Demo

GaugeVision

The goal is to simplify gauge monitoring and tagging by using YOLOv11 pose model and QR detector.

YOLOv11OpenCVRoboFlow

• Trained a custom YOLOv11 pose model to detect keypoints on analog pressure gauges.
• Integrated OpenCV's QR code detector to read identification tags placed on or near gauges.
• Combined both outputs visually to show needle direction and QR data in one intuitive display.

Github More Details

Edge Detector GUI (Qt + OpenCV + C++)

Built an interactive desktop app using Qt and OpenCV for visualizing Sobel and Canny edge detection with real-time threshold sliders.

OpenCVQTC++

• Integrated OpenCV with Qt to enable real-time image processing using Sobel and Canny filters.
• Added dynamic UI with sliders and dropdowns for live threshold tuning and filter selection.
• Designed clean modular C++ logic with CMake for cross-platform build compatibility.

Github More Details

BLIP-1 Optimization for Efficient Image Captioning

Optimized BLIP-1 image-captioning on CPU via dynamic quantization and pruning, achieving 1.42× speedup with no accuracy loss.

Quantization L1 pruning

• Baseline BLIP-1 CPU inference in 0.69 s for correct captions.
• Applied dynamic quantization to all Linear layers, reducing latency to 0.48 s.
• Combined 30% L1 pruning + quantization for a 1.40× speedup.
• Preserved caption quality (“a man and his dog”) across all variants.

GitHub More Details

Stereo Point Cloud Reconstruction

Built a stereo vision pipeline for 3D point cloud reconstruction, achieving dense 3D models using SGBM and filtering.

OpenCV3D VisionStereo MatchingCalibration

• Developed a robust stereo vision pipeline using OpenCV to compute disparity maps and reconstruct 3D point clouds from stereo images, improving depth estimation accuracy.
• Optimized disparity computation by fine-tuning SGBM parameters and applying filtering techniques, reducing noise and enhancing 3D reconstruction quality.
• Generated and exported point clouds in PLY format, enabling seamless visualization and analysis in 3D modeling applications.

Github More Details

Defect Detection in Prints Using U-Net

Implemented a U-Net model for defect detection, achieving 95% precision and reducing manual inspection time by 50%.

Defect injectionscikit-imageAugmentation

• Implemented a U-Net-based model for defect detection, achieving 95% precision in quality assurance.
• Built an AI pipeline processing 1000+ images per day, enhancing data throughput by 25%.
• Automated defect detection reporting, delivering real-time insights to quality control teams.

Github More Details

Predictive Maintenance Using XGBoost

Built a predictive maintenance model using XGBoost, achieving high accuracy in failure prediction for industrial systems.

XGBoost

XGBoostPythonData filtering

• Developed an end-to-end predictive maintenance model leveraging XGBoost for industrial failure prediction.
• Achieved 98% accuracy by tuning model hyperparameters and implementing advanced analytics.
• Automated reporting and insights generation, enhancing operational efficiency.

Github More Details

Reinforcement Learning for RRR Robot

Implemented a RL model for end effector path planning, optimizing robot arm trajectories in a 3D environment.

Reinforcement Learning

MATLABPythonKinematics

• Developed and implemented RL-based trajectory optimization in MATLAB, improving end-effector accuracy by 30% in reaching target positions.
• Trained the robot over 1,000 episodes using reward-based learning, reducing path deviation by 25% and ensuring efficient motion planning.
• Simulated and validated RL policies in MATLAB, achieving an 85% success rate in autonomously selecting optimal paths for task execution.

Github More Details

ECG Signal Classification with AI

Developed a deep learning model for classifying ECG signals, achieving 99% accuracy in detecting cardiac anomalies.

ECG / BiosignalsMATLABSignal Processing

• Developed a deep learning model in Python for ECG signal classification, achieving 99% accuracy in detecting abnormal heart rhythms.
• Preprocessed and segmented raw ECG data, improving model training efficiency by 40% through feature extraction and noise reduction.
• Optimized model inference speed, reducing prediction time by 30%, enabling real-time arrhythmia detection for potential clinical applications.

Github More Details

Get in Touch

Contact Me