Claims you can check
Each card points at something real — open the source and verify for yourself.
- StatedRésumé
CrimeVision AI
Engineered a next-generation AI surveillance platform designed for proactive criminal detection using real-time CCTV feeds and archived video footage. Implemented sketch-to-image synthesis using Cycle GAN. Integrated InsightFace for face recognition. Developed a frame-optimization algorithm and built a full-stack solution with FastAPI and ReactJS.Check source - StatedRésumé
Float Chat AI- RAG-Based Chatbot
Developed an AI-powered conversational interface that enables natural-language querying of ARGO oceanographic data. Designed a hybrid FAISS + PostgreSQL architecture and implemented an intelligent query pipeline using a Gemini LLM with map-based selection and ECharts visualizations.Check source - StatedRésuméDeveloped a computer vision–based defect detection system for fruits and vegetables deployed on Raspberry Pi and NVIDIA Jetson Orin Nano. Built custom camera-to-laser calibration using Homography Matrix. Developed a video-based AI system using VideoMAE to monitor store staff activities from CCTV footage and deployed the pipeline on E2E Networks cloud.
- StatedRésumé
MACHINE LEARNING INTERN @ KisanKonnect Safe Foods
Developed a computer vision-based defect detection system for fruits and vegetables in warehouse tray setups. Implemented position mapping of defective products and designed a laser-based indication system. - StatedRésumé
MACHINE LEARNING INTERN @ C-DAC
Developed a comprehensive system for facial analysis, integrating recognition, detection, and crowd-based object tracking. Deployed on NVIDIA Jetson Xavier NX and embedded into a humanoid drone framework within an Agile cycle. - StatedRésumé
Hack With Gujarat 2025 Winner
Winner of Hack With Gujarat 2025 - StatedRésumé
IEEE Presentation
IEEE Presentation certificate - StatedRésumé
VibeHack by Lovable
VibeHack by Lovable certificate
What Mit can prove
Proven Unproven
- Cycle GAN: self-declared, 1 evidence items, linked to Project: CrimeVision AI
- E2E Networks: self-declared, 0 evidence items
- Embeddings: self-declared, 0 evidence items
- FastAPI: self-declared, 1 evidence items, linked to Project: CrimeVision AI
- Firebase: self-declared, 0 evidence items
- Gemini LLM: self-declared, 1 evidence items, linked to Project: Float Chat AI- RAG-Based Chatbot
- Homography Matrix: self-declared, 0 evidence items
- HTML: self-declared, 0 evidence items
- HuggingFace: self-declared, 0 evidence items
- InsightFace: self-declared, 1 evidence items, linked to Project: CrimeVision AI
- JavaScript: self-declared, 0 evidence items
- Jupyter Notebook: self-declared, 0 evidence items
- LLM Finetuning (LoRA, QLoRA): self-declared, 0 evidence items
- LLM’s: self-declared, 0 evidence items
- MySQL: self-declared, 0 evidence items
- NLP: self-declared, 0 evidence items
- NVIDIA Jetson Orin Nano: self-declared, 0 evidence items
- OpenCV: self-declared, 0 evidence items
- PostgreSQL: self-declared, 1 evidence items, linked to Project: Float Chat AI- RAG-Based Chatbot
- Python: self-declared, 0 evidence items
- Pytorch: self-declared, 0 evidence items
- RAG: self-declared, 1 evidence items, linked to Project: Float Chat AI- RAG-Based Chatbot
- Raspberry PI: self-declared, 0 evidence items
- ReactJS: self-declared, 1 evidence items, linked to Project: CrimeVision AI
- Roboflow: self-declared, 0 evidence items
- SQL: self-declared, 0 evidence items
- TypeScript: self-declared, 0 evidence items
- Vector Databases (FAISS, ChromaDB): self-declared, 0 evidence items
- Vector Search: self-declared, 0 evidence items
- VideoMAE: self-declared, 0 evidence items
- Visual Studio Code: self-declared, 0 evidence items
- VLM’s: self-declared, 0 evidence items
- YOLO: self-declared, 0 evidence items
Shipped work
See all workFlagship systems this candidate architected will appear here once attached to the dossier. No project has been added yet.
Getting better, on the record
Proven skills over time — today marked in lime.
This trajectory populates once the candidate completes scored interview sessions. No score has been recorded or estimated here.
Career chronology
Gaps shown honestly — only what's on the record.
MACHINE LEARNING ENGINEER
KisanKonnect Safe Foods
C-DAC
PGCP
MACHINE LEARNING INTERN
KisanKonnect Safe Foods
VibeHack by Lovable
IEEE Presentation
Hack With Gujarat 2025 Winner
MACHINE LEARNING INTERN
C-DAC
Bharati Vidyapeeth College of Engineering
Bachelor of Engineering
H.M.B Sardar High School
HSC
Hiring for AIML Engineer?
Request the full evidence dossier — verified interview sessions, cryptographically attested artifacts, and reference outcomes.
Goes straight to Mit. No recruiter spam.