Exploring the
edge of
intelligence.
Undergrad CSE student learning to architect complex data pipelines and AI systems.
AI Engineer & Problem Solver
I'm a Computer Science Engineering student at IIIT Sri City (Graduating 2027) working at the intersection of AI research and production systems. Currently my interests include edge-native LLM inference using compute strategies with NPUs, and building RAG systems that work locally without cloud dependencies.
My experience spans building AI-driven tools at Evil Genius Games, RAG Evaluation using LangSmith, developing geospatial data pipelines at LightMetrics, and implementing research papers in GANs, crowd counting, and other algorithms.
Core Competencies
RAG & LLM Systems
Advanced RAG architectures with hybrid search, vector databases, and RAG evaluations using LangSmith
Edge AI & Inference
Researching heterogeneous compute strategies for NPU-based LLM inference using VitisAI and RyzenAI with model quantization.
Cloud & DevOps
Building cloud-native systems on GCP with Docker, Kubernetes, NGINX load balancing, and CI/CD pipelines.
Computer Vision
Implementing various architectures with different applications in the field, from crowd counting to image to image transalation.
Data Engineering
Postgres procedures, API integration, and automated data validation pipelines.
Real Work Experience
Working on real world projects that utilize and enhance these skills further.
Edge-Native LLM Inference
Bachelor's thesis researching heterogeneous compute strategies for LLM inference on NPUs using VitisAI and RyzenAI, with model quantization and local RAG system integration.
Cloud-Native RAG System (GCP)
Scalable document chat system using Cloud Run, Cloud Build, and API Gateway. Containerized with Docker and load-balanced with NGINX.
FlounderNet - Crowd Counting
Implemented efficient architecture for crowd counting with multi-modal data fusion to enhance model representation and performance.