I build AI-powered applications, retrieval-augmented generation pipelines, and backend systems using Python and modern AI technologies. My experience spans AI application development, cloud-based workflows, IoT analytics, and applied research.
I am an AI Engineer completing my B.Tech in Artificial Intelligence (2022–2026) at Amity University with an 8.44 CGPA. My core engineering practice focuses on designing robust AI application architectures, high-performance RAG pipelines, and production backend services using Python, FastAPI, and modern AI stacks.
My work spans applied deep learning, large language models, agentic workflows, computer vision, and privacy-preserving distributed machine learning. Through both production engineering at Lucidus AI and research R&D at CSIR–National Physical Laboratory, I have engineered scalable data ingestion pipelines, cloud-native deployments across AWS and GCP, and telemetry anomaly detection systems.
Beyond system development, I am active in peer-reviewed research with IEEE conference publications in IoT-AI analytics and privacy-preserving frameworks. In leadership, I have served as Chairperson of the IEEE Student Branch and President of the Hardly Human AI Club, fostering collaborative technical communities and competitive engineering hackathons.
Amity University (2022 – 2026) · CGPA: 8.44. Specialization in Machine Learning, Neural Networks & Autonomous Systems.
National Physical Laboratory, CSIR (Govt. of India) · Engineered dual-mode IoT storage pipelines and anomaly detection on telemetry.
Chairperson, IEEE Student Branch & President, Hardly Human AI Club · Spearheaded hackathons, workshops, and student research culture.
Verified technologies and architectural competencies demonstrated across production systems, prototypes, and applied research.
A collection of intelligent systems, RAG pipelines, distributed learning frameworks, and deep learning estimators built with production engineering rigor.
A network telemetry intelligence and analytics platform engineered to automate root-cause analysis for complex network infrastructure incidents.
A distributed, privacy-preserving machine learning framework designed to train AI models across decentralized consumer and industrial IoT nodes without exposing raw datasets.
A deep learning framework engineered for accurate UAV kinematic parameter estimation (Range, Velocity, and Direction of Arrival) in high-noise environments.
A lightweight, IoT-compatible edge computer vision pipeline designed for real-time situational analysis and emergency gesture detection.
A multimodal retrieval-augmented generation application integrating joint image-text embeddings for context-aware botanical identification and diagnostic querying.
A sensor-integrated predictive monitoring system coupling IoT telemetry pipelines with statistical machine learning models for early-stage fluid leakage identification.
A specialized generative pipeline transforming complex natural language spatial descriptions into parametric OpenSCAD scripts for rapid 3D CAD prototyping.
Peer-reviewed publications and conference contributions in artificial intelligence, privacy-preserving distributed systems, and computer vision.
Conference: 2025 3rd International Conference on Communication, Security, and Artificial Intelligence (ICCSAI)
Conference: 2025 Second International Conference on Pioneering Developments in Computer Science & Digital Technologies (IC2SDT)
Conference: 2026 3rd International Conference on Advanced Computing Technologies (ICACT)
Led university-wide technical initiatives, managed executive committees, organized technology symposia, and cultivated student research and innovation programs.
Directed AI-focused collaborative workshops, project incubations, and developer meetups centered on practical machine learning and generative AI workflows.
1st Position — Rhapsody 3.0
March 20251st Runner Up
February 2024Top 10 in Intel AI Hackathon
December 2024Oracle · Issued October 2025
Oracle · Issued October 2025
Cisco Networking Academy · Issued July 2025
DeepLearning.AI & OpenAI · Issued June 2024
I am always excited to discuss engineering roles, applied AI research opportunities, and collaborations in Generative AI, RAG, and scalable machine learning systems.