AI Engineer and AI Evaluation Specialist specializing in building multimodal systems, LLM orchestration, RAG pipelines, backend architecture, and cloud infrastructure.
I am an AI Engineer and AI Evaluation Specialist dedicated to crafting sophisticated AI systems that solve real-world problems. My focus lies at the intersection of large language models, multimodal evaluations, robust backend architectures, and secure cloud infrastructures.
With hands-on experience spanning model output evaluation, custom video streaming pipeline engineering (FFmpeg/HLS), scalable cloud architectures (AWS), and local-first AI system design, I deliver production-grade solutions optimized for performance and accuracy.
Expertise in RAG, prompt engineering, LangChain, and LLM orchestration.
AI data training, output annotation, model evaluation, and preference ranking.
Scalable architectures built using Python, Flask, Django, and SQL databases.
High-performance AWS infrastructure deployment, Docker, and HLS Streaming.
A curated showcase of local-first AI assistants, mobile chat companions, and innovative AI tools built by me.
A local-first multimodal AI assistant supporting text, voice, and image interactions using modern LLMs and vision models.
AI-powered Android chat companion application featuring persona-based conversational workflows and dynamic AI interactions.
Real-world client engagements involving OTT infrastructure, cloud architecture, backend systems, and enterprise platforms.
Contributing to the development of a highly scalable, enterprise-grade e-commerce content management system designed to streamline online retail workflows and boost operations.
STREAMFORGE is a custom OTT media processing and distribution platform built to automate video ingestion, transcoding, storage, and global delivery.
Key achievements and contributions in the AI space
Presented research paper 'Performance Analysis of Machine Learning Algorithms for Brain Stroke Prediction' at a national e‑Conference.
Contributed to AI training workflows for image preference datasets through large-scale annotation, evaluation, and quality review processes.
Completed AI evaluation, annotation, ranking, and quality review workflows across multimodal datasets in production environments.
Always open to discussing AI systems, automation, and collaborative innovation.