Kathiravan Arumugam

AI/ML Engineer Trainee

Bangalore, IndiaArtificial Intelligence / Machine Learning
1roles
51skills
2education

About

AI/ML Engineer with one year of post-graduation industry trainee experience building production-oriented generative AI, RAG, computer vision, OCR, and object detection/segmentation solutions.

Experience

AI/ML Engineer Trainee

Sony India Software Centre Pvt Ltd

June 2025 - June 2026 · Bengaluru

Designed an interactive multimodal RAG system for model-training analysis with retrieval and automated reporting from logs, PDFs, and visual artifacts. Built LLM-powered workflows for multimodal document understanding and knowledge retrieval. Implemented a hierarchical agent workflow with Supervisor, Research, Scoping, and Compression agents for iterative reasoning, tool calling, and structured reports. Built video-based OCR pipelines with frame sampling, ROI extraction, preprocessing, OCR inference, and confidence stabilization. Trained segmentation and object-detection models using MMDetection and evaluated them using mAP, precision-recall metrics, and confidence-threshold tuning.

Education

Nadar Saraswathi College of Engineering and Technology

BE, Electronics & Communication Engineering

Oct 2020 - May 2024

CGPA: 8.6

Professional course, Python Full stack development

Oct 2024 - May 2025

Skills

PythonLangChainLangGraphFastAPIPyTorchGenerative AIRetrieval-Augmented Generation (RAG)Computer VisionOCRObject DetectionImage SegmentationMMDetectionYOLOCNNsOpenCVHugging Face TransformersMultimodal LLMsGemma-3Prompt EngineeringModel Context Protocol (MCP)GPU TrainingmAPPrecision-Recall AnalysisConfidence Threshold TuningHyperparameter OptimizationNumPyPandasHTMLCSSSQLDockerCI/CD PipelinesGitHub ActionsModel DeploymentTensorRTONNXLinuxCondaGitGitHubAWS EC2AWS S3AWS Cloud DeploymentCUDAChromaDBGradioOpenRouterTavily Search APIPydanticPaddle OCRTrOCR

Projects

Interactive Multimodal RAG Chatbot with Automated PDF Reporting for Model Training Analysis

Designed and developed an interactive multimodal RAG chatbot using Gemma-3 (12B) to analyze model training reports and logs. Implemented a RAG pipeline over PDFs using MiniLM text embeddings and SigLIP image embeddings for visual-aware retrieval; extracted PDF images and generated contextual captions with a multimodal LLM. Built automated PDF reporting that consolidates YAML configurations, training logs, images, prompts, and LLM analysis, along with a Gradio UI for contextual Q&A, follow-up suggestions, and downloadable reports. Used Python, PyTorch, Hugging Face Transformers, CUDA, LangChain, ChromaDB, SigLIP, and Gradio.

AI-Powered Multi-Agent Deep Research System

Designed and developed a LangGraph-based multi-agent research system with agents for query clarification, research planning, web search, evidence synthesis, and report generation. Implemented hierarchical Supervisor, Research, Scoping, and Compression agents; integrated OpenRouter and Tavily Search API; built a FastAPI backend for REST APIs; and extended the platform with MCP support for local files, PDFs, and GitHub repositories. Used Python, LangGraph, LangChain, FastAPI, OpenRouter, Tavily Search, MCP, and Pydantic.

Real-Time Pothole Detection & Segmentation Pipeline

Developed a Mask R-CNN (ResNet-50 + FPN) instance-segmentation system for pothole detection. Built preprocessing, model-training, and evaluation pipelines using MMDetection; achieved 0.72 mAP; addressed varying lighting, road textures, and occlusions; and accelerated inference with TensorRT FP16 to approximately 9.58 ms latency. Used Python, PyTorch, MMDetection, OpenCV, Docker, and TensorRT.

Video-Based OCR Pipeline with Confidence Stabilization

Developed an end-to-end OCR system for extracting structured text from videos using frame sampling, ROI extraction, and preprocessing. Implemented confidence normalization, temporal stabilization, numeric validation, noise removal, and error-correction rules, and evaluated OCR performance across diverse video conditions. Used Python, OpenCV, Paddle OCR, TrOCR, NumPy, and Pandas.