Premith Kumar Chilukuri

Machine Learning Engineer and AI Researcher

I'm Premith, I Specialize in developing cutting-edge AI technologies and innovative applications, I bring a blend of research acumen and practical engineering to solve complex problems. I have previous previous work-experiences at Virginia Tech, Samsung R&D Institute, Supervue Ai, and Zebi Data. My passion lies in building AI products and services to enhance business processes, data privacy, process automation, and user experiences.

Let's connect and explore how we can leverage AI to create transformative solutions. Open to opportunities that challenge the status quo and drive innovation.

More about my work experience

Work Experience

AI Researcher & Graduate Research Assistant

Virginia Tech/ May 2023 - Present

Spearheading generative AI research with significant achievements in LLM-based web chatbots and novel AI models for design automation and data privacy. My contributions have led to top-tier conference publications and advancements in federated AI research

Lead Machine Learning Engineer

Supervue Ai / Jan 2020 - Jan 2023

Led the AI application team, developing high-accuracy facial recognition technologies and real-time vision-based surveillance systems which was used to .monitor 1.3M students across India for the National Testing Agency. I also pioneered the development of India’s first Social Distance Monitoring app using patented one-shot object-flow regression method

Research Collaborator

Samsung R&D Institute / Oct 2021 - Aug 2022

Innovated in video inpainting algorithms for mobile devices, achieving notable performance improvements and patenting transformative technologies.

Machine Learning Engineer

Zebi Data / Dec 2018 - Dec 2019

Developed and deployed India’s first blockchain-assisted autonomous hotel check-in system, featuring AI-based biometrics verification and ID-card OCR.

My Resume

More about my research, projects, & skills

Research Papers

&

Patents

Primary inventor of a patented technology: Dynamic Auto-Calibration System, IP India Patent App No: 202041034063

Inventor of a Collaborative Patent: n-Neighborhood Temporal Feature Transformation between Samsung R&D and Andhra University, App No: 202241043300

Author of Generating Optimized 3D Designs For Manufacturing Using a Guided Voxel Diffusion Model, Published in AAAI Conference

Author of AMMDAS: Multi-Modular DAS with Generative Masks Processing, Published in IEEE Access Journal

Author of l, r-Stitch Unit: Encoder-Decoder-CNN Based Image-Mosaicing, Published in IEEE Access Journal

Author of Attention Based Multi-Patched 3D-CNNs with Hybrid Fusion Architecture, Published in JCC Journal

Show Publication

More about my projects

Recent Projects

LLM Powered Multi-User Video Conferencing Application with Automated Meeting Minutes

Jan 2023 - May 2023

Developed Python, JS, and WebRTC based video conferencing app leveraging GPT API for automated meeting minutes generation (ASR-transcribed meeting audio). Resulted in 30% time savings. Used Express JS for secured HTTP requests to stream app media.

Zero-Shot Video Question Answering Using CLIP, CLAP, and Falcon-7.5B Models [Demo]

Sept 2023 - Jan 2024

Built a Video-Question-Answering web-application by integrating Falcon-7.5B LLM based RAG pipeline on audio & video context extracted using CLIP & CLAP models. Outperformed 10x larger Flamingo-80B model on multiple Video-QA benchmarks

More Details

More about my skills and expertise

Technical Skills

Domain Expertise

Generative AI, Computer Vision, NLP, Deep Learning, Machine Learning, App Development, Data Engineering, and MLOps

Languages

Python, Go, Java, C++, C, JavaScript, SQL

Tools & Technologies

TensorFlow, PyTorch, ONNX, Docker, Kubernetes, AWS, Azure, Git, GraphQL, Redis, Kafka, and more